From cf4e0a4383c44b7168487aed8c97547c7f99ed2c Mon Sep 17 00:00:00 2001 From: Carlos Eduardo Arango Gutierrez Date: Mon, 21 Sep 2026 11:23:36 +0200 Subject: [PATCH 1/9] chore(recipes): bump kueue to 0.19.5 and slinky-slurm charts to 1.2.2 Four pins from the 2026-09-21 drift report, grouped because all four are mechanical: no AICR values change is required by any of them. kueue 0.19.3 -> 0.19.5. The component carries a hand-maintained copy of the chart's controllerManagerConfigYaml that Helm does not merge, so every bump has to re-diff that blob against upstream and re-apply the integrations .frameworks trim. This time the blob is byte-identical between 0.19.3 and 0.19.5, so the re-pin is a verified no-op: nothing to adopt, nothing dropped. AICR's copy still differs from the 0.19.5 default by exactly the documented trim and nothing else. CRD templates are byte-identical, and v1beta2 remains served and stored for resourceflavors/clusterqueues/localqueues, so the three bundled quota manifests keep their apiVersion. The only rendered change beyond the image tag is kueue-manager-role gaining delete on trainer.kubeflow.org/trainjobs, which is upstream-intended; TrainJob is one of the three frameworks AICR keeps, so the widening is real and worth naming. 0.19.4 fixes TrainJob admission dropping runtime-defined tolerations when ResourceFlavor tolerations apply, which AICR triggers both halves of. slinky-slurm, slinky-slurm-operator and slinky-slurm-operator-crds 1.2.0 -> 1.2.2, together: the operator chart declares a dependency on slurm-operator-crds at the same version, so a partial bump would cross it. The slurm chart's values.yaml is byte-identical across the bump and the CRDs render byte-identical, all six kinds still v1beta1 served and stored. The operator adds one key, metricsSecure, defaulting false. Both maintenance contracts were re-verified rather than assumed: certManager.enabled=true and crds.enabled=false still match the 1.2.2 chart defaults, and the three Alpine sidecars are still :latest upstream, so AICR's 3.23.3 pins stay. 1.2.2 adds a minimum-slurm-version annotation of 25.11; the pinned 26.05 pyxis images clear it, so no digest moves. The version constant in TestComponentRegistry_SlinkySlurmChartVersions moves with the pins. It is a lockstep guard whose whole purpose is to track them, and it was observed red against the new pins before being updated, so it still discriminates. Golden parity files were regenerated with AICR_UPDATE_GOLDEN=1; the diff touches exactly the seven *-training-slurm leaves and no other leaf. kueue produces no golden change because no overlay or mixin references it. No ADR-021 record is required: no CRD delta, no removed or renamed values path, no API- or stored-version movement in either family. Signed-off-by: Carlos Eduardo Arango Gutierrez --- docs/user/container-images.md | 14 +-- pkg/bundler/testdata/stock_render_golden.yaml | 118 +++++++++--------- pkg/recipe/components_test.go | 2 +- .../testdata/catalog_parity_golden.yaml | 14 +-- recipes/checks/kueue/health-check.yaml | 4 +- .../health-check.yaml | 2 +- recipes/components/kueue/values.yaml | 2 +- .../slinky-slurm-operator/values.yaml | 2 +- recipes/registry.yaml | 8 +- 9 files changed, 83 insertions(+), 83 deletions(-) diff --git a/docs/user/container-images.md b/docs/user/container-images.md index b08945a30a..7e02805c77 100644 --- a/docs/user/container-images.md +++ b/docs/user/container-images.md @@ -56,7 +56,7 @@ _Rendering fidelity:_ `catalog-parity: charts are rendered with the shared recip | kai-scheduler | helm | kai-scheduler | v0.16.9 | 12 | | kube-prometheus-stack | helm | prometheus-community/kube-prometheus-stack | 84.4.0 | 8 | | kubeflow-trainer | helm | kubeflow-trainer | 2.2.0 | 4 | -| kueue | helm | kueue | 0.19.3 | 1 | +| kueue | helm | kueue | 0.19.5 | 1 | | mariadb-operator | helm | mariadb-operator | 26.6.0 | 1 | | mariadb-operator-crds | helm | mariadb-operator-crds | 26.6.0 | 0 | | network-operator | helm | nvidia/network-operator | 26.4.1 | 12 | @@ -75,9 +75,9 @@ _Rendering fidelity:_ `catalog-parity: charts are rendered with the shared recip | prometheus-adapter | helm | prometheus-community/prometheus-adapter | 5.3.0 | 1 | | prometheus-adapter-ocp | helm | prometheus-community/prometheus-adapter | 5.3.0 | 1 | | prometheus-operator-crds | helm | prometheus-community/prometheus-operator-crds | 28.0.1 | 0 | -| slinky-slurm | helm | slurm | 1.2.0 | 5 | -| slinky-slurm-operator | helm | slurm-operator | 1.2.0 | 2 | -| slinky-slurm-operator-crds | helm | slurm-operator-crds | 1.2.0 | 0 | +| slinky-slurm | helm | slurm | 1.2.2 | 5 | +| slinky-slurm-operator | helm | slurm-operator | 1.2.2 | 2 | +| slinky-slurm-operator-crds | helm | slurm-operator-crds | 1.2.2 | 0 | | slinky-topograph | helm | topograph/topograph | 1.0.0 | 1 | | slurm-accounting-mariadb | helm | mariadb-cluster | 26.6.0 | 0 | @@ -245,7 +245,7 @@ _No images extracted._ ### kueue -- `registry.k8s.io/kueue/kueue:v0.19.3` +- `registry.k8s.io/kueue/kueue:v0.19.5` ### mariadb-operator @@ -352,8 +352,8 @@ _No images extracted._ ### slinky-slurm-operator -- `ghcr.io/slinkyproject/slurm-operator-webhook:1.2.0` -- `ghcr.io/slinkyproject/slurm-operator:1.2.0` +- `ghcr.io/slinkyproject/slurm-operator-webhook:1.2.2` +- `ghcr.io/slinkyproject/slurm-operator:1.2.2` ### slinky-slurm-operator-crds diff --git a/pkg/bundler/testdata/stock_render_golden.yaml b/pkg/bundler/testdata/stock_render_golden.yaml index f2fc489099..437d369155 100644 --- a/pkg/bundler/testdata/stock_render_golden.yaml +++ b/pkg/bundler/testdata/stock_render_golden.yaml @@ -1067,28 +1067,28 @@ gb200-eks-ubuntu-training-slurm: 015-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 016-slinky-slurm-operator-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-slinky-slurm-operator-crds/install.sh: b763afb19a730721e43f3a5be956d4ff183eb0623c8e3c168544ad26e8fbb46f - 016-slinky-slurm-operator-crds/upstream.env: 1c777d58b5c1b98b87458662de44a517d6ad83a9ce4db2fc48d138bfce3588f7 + 016-slinky-slurm-operator-crds/upstream.env: 4d0a2be7546b7bf8bc9469de1609fdaca2af94c51f77882e050878f5820e2b88 016-slinky-slurm-operator-crds/values.yaml: f6ded79ccc11132cec0b9dbbf1248ba5862248b9e4daea35c21e60e28c078b12 017-slinky-slurm-operator/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-slinky-slurm-operator/install.sh: 01a221b08c6dc5193b45aa8a1806e6962960068b181d14d10d04675b4c3621d9 - 017-slinky-slurm-operator/upstream.env: 26b9cd7773cbf321f6fb36fc6011219ef44eacffd2595522466b74807499eb02 + 017-slinky-slurm-operator/upstream.env: f359e532717f31dece6765590458939931c5fe6cfeea774c9441ad360036ec54 017-slinky-slurm-operator/values.yaml: d40d9941ddd05279343fad2c98b2f3c8ac5cb2e2459266e63d1937adab908e60 - 018-slinky-slurm-pre/Chart.yaml: fec67bce3bf4db7adc7a031a87ca73d7e6230715ef4a2f88ca38e7c8a6439a67 + 018-slinky-slurm-pre/Chart.yaml: f65c7669d78ddb55eeccb55768259568f88ceb23bc0853a325ebdefbab18a6a0 018-slinky-slurm-pre/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 018-slinky-slurm-pre/install.sh: 81a42ad3d2342f567074c56e5e18a07b665ff8eb934c12ae91594ab2c4abb4e3 - 018-slinky-slurm-pre/templates/compute-domain.yaml: 620fdd58695c404a2b535415573fbc4320b8dada589dddf7ed3ce889aacf7cc2 + 018-slinky-slurm-pre/templates/compute-domain.yaml: 41b9c84d6d9067f4eb2daf0fedd540a33c01eac04b70816e2aee6737e9da3a8a 018-slinky-slurm-pre/templates/enroot-config.yaml: c90815614101b5b1299602c1a89863bb31e98c16e219a9d3e6497f321e140954 018-slinky-slurm-pre/values.yaml: 36b3e905ded091f970dd6ad98389be8e4a6481afffb6682b66370558fa99a393 019-slinky-slurm/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 019-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb - 019-slinky-slurm/upstream.env: ae0598bf066c26ec0f76503212f4c50dc09103750aa36700e514fcfcbaad8c30 + 019-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 019-slinky-slurm/values.yaml: 36b3e905ded091f970dd6ad98389be8e4a6481afffb6682b66370558fa99a393 - README.md: cd743008c0568e64613a3621351bdaa2504bf9f365c7702065f27bc064ebc1fa + README.md: 3fa761f45ca96954b4610e1a44e9ee4dc63d1e0fd444b9d7230ea92f337258e5 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 9905ee9008d86ae458d7f11ace060abf90c8c9199e9bbbbe9b82b72bf31f730a - checksums.txt: 3f05044bd2bbd368e50d408f415f27f4df38aff8cf29231ca9eb766760043697 + bundle-info.yaml: ed5acd5680a95d06ced55ae4de50b14aaaf19dc069e4ad7bf573366d9967fe58 + checksums.txt: d1e2534ed16e8835cd9eb2b44b7c60652f798a6689b351301a3eb165647e4932 deploy.sh: 3bf1475ef39efa155a2cdff6c99ffeba55d931adf38871f8bc74467845584eae - recipe.yaml: e0d3e329aff972080d3f76604ad6d18971fe685190ceb7e6753e06473640bf8e + recipe.yaml: 36769eeeb1ec16f6b5371fe31c82024a55ff0e0d2b2cadb0ac6687d399655bec gb200-gke-cos-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -1343,28 +1343,28 @@ gb200-gke-cos-training-slurm: 015-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 016-slinky-slurm-operator-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-slinky-slurm-operator-crds/install.sh: b763afb19a730721e43f3a5be956d4ff183eb0623c8e3c168544ad26e8fbb46f - 016-slinky-slurm-operator-crds/upstream.env: 1c777d58b5c1b98b87458662de44a517d6ad83a9ce4db2fc48d138bfce3588f7 + 016-slinky-slurm-operator-crds/upstream.env: 4d0a2be7546b7bf8bc9469de1609fdaca2af94c51f77882e050878f5820e2b88 016-slinky-slurm-operator-crds/values.yaml: f6ded79ccc11132cec0b9dbbf1248ba5862248b9e4daea35c21e60e28c078b12 017-slinky-slurm-operator/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-slinky-slurm-operator/install.sh: 01a221b08c6dc5193b45aa8a1806e6962960068b181d14d10d04675b4c3621d9 - 017-slinky-slurm-operator/upstream.env: 26b9cd7773cbf321f6fb36fc6011219ef44eacffd2595522466b74807499eb02 + 017-slinky-slurm-operator/upstream.env: f359e532717f31dece6765590458939931c5fe6cfeea774c9441ad360036ec54 017-slinky-slurm-operator/values.yaml: d40d9941ddd05279343fad2c98b2f3c8ac5cb2e2459266e63d1937adab908e60 - 018-slinky-slurm-pre/Chart.yaml: fec67bce3bf4db7adc7a031a87ca73d7e6230715ef4a2f88ca38e7c8a6439a67 + 018-slinky-slurm-pre/Chart.yaml: f65c7669d78ddb55eeccb55768259568f88ceb23bc0853a325ebdefbab18a6a0 018-slinky-slurm-pre/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 018-slinky-slurm-pre/install.sh: 81a42ad3d2342f567074c56e5e18a07b665ff8eb934c12ae91594ab2c4abb4e3 - 018-slinky-slurm-pre/templates/compute-domain.yaml: 620fdd58695c404a2b535415573fbc4320b8dada589dddf7ed3ce889aacf7cc2 + 018-slinky-slurm-pre/templates/compute-domain.yaml: 41b9c84d6d9067f4eb2daf0fedd540a33c01eac04b70816e2aee6737e9da3a8a 018-slinky-slurm-pre/templates/enroot-config.yaml: c90815614101b5b1299602c1a89863bb31e98c16e219a9d3e6497f321e140954 018-slinky-slurm-pre/values.yaml: 36b3e905ded091f970dd6ad98389be8e4a6481afffb6682b66370558fa99a393 019-slinky-slurm/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 019-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb - 019-slinky-slurm/upstream.env: ae0598bf066c26ec0f76503212f4c50dc09103750aa36700e514fcfcbaad8c30 + 019-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 019-slinky-slurm/values.yaml: 36b3e905ded091f970dd6ad98389be8e4a6481afffb6682b66370558fa99a393 - README.md: 77013cccf74249773878eb911d4af2c86db0de11f2a0a186dcc14a61d73792fd + README.md: 86ca6a2e60ef1ce0b5bc9ac9a5096a956e9ac0bd8e4cee2755c8509f5e551425 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: d2be07c4bd13419a9c0f7e71a0e3abcad9329f9a51a7aed9765d6997f690e0de - checksums.txt: 161f7c24292ba1caef47d090a14a43dd1c5bf2067571453ee1ca1f576ee29223 + bundle-info.yaml: f9621467f7863c82a9587f31f6e5e442de91a6c3c220182c15406b046ad52e61 + checksums.txt: 47b034b40186b5b1f80891d9a1c00278bd16e65614d4842a2a7595e2d38623f8 deploy.sh: ef955644171896a717b59c2582b0fbef5b6cab0d2f67c89924656b3aee005c73 - recipe.yaml: 0cf270c23abb5c143982232de0b6115c9502e29392acfaab8de683edc8398f18 + recipe.yaml: 1bc779869631a37d7bc3cb49313e57bc577f8aa0a99ce4992dddc968564910bc gb200-oke-ubuntu-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -1813,28 +1813,28 @@ gb300-eks-ubuntu-training-slurm: 015-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 016-slinky-slurm-operator-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-slinky-slurm-operator-crds/install.sh: b763afb19a730721e43f3a5be956d4ff183eb0623c8e3c168544ad26e8fbb46f - 016-slinky-slurm-operator-crds/upstream.env: 1c777d58b5c1b98b87458662de44a517d6ad83a9ce4db2fc48d138bfce3588f7 + 016-slinky-slurm-operator-crds/upstream.env: 4d0a2be7546b7bf8bc9469de1609fdaca2af94c51f77882e050878f5820e2b88 016-slinky-slurm-operator-crds/values.yaml: f6ded79ccc11132cec0b9dbbf1248ba5862248b9e4daea35c21e60e28c078b12 017-slinky-slurm-operator/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-slinky-slurm-operator/install.sh: 01a221b08c6dc5193b45aa8a1806e6962960068b181d14d10d04675b4c3621d9 - 017-slinky-slurm-operator/upstream.env: 26b9cd7773cbf321f6fb36fc6011219ef44eacffd2595522466b74807499eb02 + 017-slinky-slurm-operator/upstream.env: f359e532717f31dece6765590458939931c5fe6cfeea774c9441ad360036ec54 017-slinky-slurm-operator/values.yaml: d40d9941ddd05279343fad2c98b2f3c8ac5cb2e2459266e63d1937adab908e60 - 018-slinky-slurm-pre/Chart.yaml: fec67bce3bf4db7adc7a031a87ca73d7e6230715ef4a2f88ca38e7c8a6439a67 + 018-slinky-slurm-pre/Chart.yaml: f65c7669d78ddb55eeccb55768259568f88ceb23bc0853a325ebdefbab18a6a0 018-slinky-slurm-pre/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 018-slinky-slurm-pre/install.sh: 81a42ad3d2342f567074c56e5e18a07b665ff8eb934c12ae91594ab2c4abb4e3 - 018-slinky-slurm-pre/templates/compute-domain.yaml: 620fdd58695c404a2b535415573fbc4320b8dada589dddf7ed3ce889aacf7cc2 + 018-slinky-slurm-pre/templates/compute-domain.yaml: 41b9c84d6d9067f4eb2daf0fedd540a33c01eac04b70816e2aee6737e9da3a8a 018-slinky-slurm-pre/templates/enroot-config.yaml: c90815614101b5b1299602c1a89863bb31e98c16e219a9d3e6497f321e140954 018-slinky-slurm-pre/values.yaml: ef75bbe2e03bc4b1cf4c4f4456b31d470a7bcce3ca243af1891f9dada650c6f6 019-slinky-slurm/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 019-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb - 019-slinky-slurm/upstream.env: ae0598bf066c26ec0f76503212f4c50dc09103750aa36700e514fcfcbaad8c30 + 019-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 019-slinky-slurm/values.yaml: ef75bbe2e03bc4b1cf4c4f4456b31d470a7bcce3ca243af1891f9dada650c6f6 - README.md: 7ec5178e47106fc572219ead6a6e1a8c91177ab6c48edeedfc37f699a64b3067 + README.md: e68c8b287f190c56a33b6a72d098110a878cb9a52ad70f8ffc521662fb1cba8b UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: e6ec5054f3016420f86e78c3473cc0786b01d7e7437389b28700226bf968ffa3 - checksums.txt: 5e0f22b09af08c40532c3f8dfb61b88c654cd4cb22c62935c6c76b85f5310b60 + bundle-info.yaml: 8997a0e021a97fcd4ec0382679820778200c399bf66554c4f2c842f8e0657705 + checksums.txt: dd4811e996e6d0c9a9ae16b0651e5dc6e8852933463f62e17871c45b27f7b468 deploy.sh: 3bf1475ef39efa155a2cdff6c99ffeba55d931adf38871f8bc74467845584eae - recipe.yaml: c711fe632ed29fa531c91eed1bf43f0b04c985168f3f07df85030a7cce6b4f08 + recipe.yaml: e8ae72ec3e1bf9e91198a0246ab80e8d534994d995c475511a2c4f5f80e48e53 gb300-generic-ubuntu-training: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -2152,27 +2152,27 @@ h100-aks-ubuntu-training-slurm: 015-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 016-slinky-slurm-operator-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-slinky-slurm-operator-crds/install.sh: b763afb19a730721e43f3a5be956d4ff183eb0623c8e3c168544ad26e8fbb46f - 016-slinky-slurm-operator-crds/upstream.env: 1c777d58b5c1b98b87458662de44a517d6ad83a9ce4db2fc48d138bfce3588f7 + 016-slinky-slurm-operator-crds/upstream.env: 4d0a2be7546b7bf8bc9469de1609fdaca2af94c51f77882e050878f5820e2b88 016-slinky-slurm-operator-crds/values.yaml: f6ded79ccc11132cec0b9dbbf1248ba5862248b9e4daea35c21e60e28c078b12 017-slinky-slurm-operator/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-slinky-slurm-operator/install.sh: 01a221b08c6dc5193b45aa8a1806e6962960068b181d14d10d04675b4c3621d9 - 017-slinky-slurm-operator/upstream.env: 26b9cd7773cbf321f6fb36fc6011219ef44eacffd2595522466b74807499eb02 + 017-slinky-slurm-operator/upstream.env: f359e532717f31dece6765590458939931c5fe6cfeea774c9441ad360036ec54 017-slinky-slurm-operator/values.yaml: d40d9941ddd05279343fad2c98b2f3c8ac5cb2e2459266e63d1937adab908e60 - 018-slinky-slurm-pre/Chart.yaml: fec67bce3bf4db7adc7a031a87ca73d7e6230715ef4a2f88ca38e7c8a6439a67 + 018-slinky-slurm-pre/Chart.yaml: f65c7669d78ddb55eeccb55768259568f88ceb23bc0853a325ebdefbab18a6a0 018-slinky-slurm-pre/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 018-slinky-slurm-pre/install.sh: 81a42ad3d2342f567074c56e5e18a07b665ff8eb934c12ae91594ab2c4abb4e3 018-slinky-slurm-pre/templates/enroot-config.yaml: c90815614101b5b1299602c1a89863bb31e98c16e219a9d3e6497f321e140954 018-slinky-slurm-pre/values.yaml: 5643ef72841c8424adbe75cfb40f99691ec60c5e6498bb3a115824a3264bce9d 019-slinky-slurm/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 019-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb - 019-slinky-slurm/upstream.env: ae0598bf066c26ec0f76503212f4c50dc09103750aa36700e514fcfcbaad8c30 + 019-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 019-slinky-slurm/values.yaml: 5643ef72841c8424adbe75cfb40f99691ec60c5e6498bb3a115824a3264bce9d - README.md: af73cb4c0d378ce9f520a8d8b8eca27b9bab58e563867071147136cb6030ab36 + README.md: 07cb6a0cf061ee1d2901ca0e90f4b9617e9a3a56cd863fb28e975e1aa5f6236f UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 916c3459e3eb96504a80c75513b36d27705f5cf0ad3d7134baed19967cf76e4c - checksums.txt: c51103017f51436cc2a1f168845508c481520316ba160c4da29ce8dfa9c3b05c + bundle-info.yaml: 50d6742738257cea4b602afcf67b7d1b99e85b3491257b10f6b6eb8d9fd65181 + checksums.txt: 3ba316c8714b057d4be855f3ac1838dd4793754a0e1502fe23b43660dd06b320 deploy.sh: 9b4d0619afbaa1425c76e4035df5a7a41bb8c10f35fd0892b7e552a3bc72d66d - recipe.yaml: e1fbd4c2236e574456d9ee80cfd4bb61dec01b33e293edfc858de6bb87d4bebb + recipe.yaml: f7bc433711c19af1be05a9ff9625276a3c6f1672931c629c48a189b5d89c409d h100-any: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -2606,27 +2606,27 @@ h100-eks-ubuntu-training-slurm: 014-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 015-slinky-slurm-operator-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 015-slinky-slurm-operator-crds/install.sh: b763afb19a730721e43f3a5be956d4ff183eb0623c8e3c168544ad26e8fbb46f - 015-slinky-slurm-operator-crds/upstream.env: 1c777d58b5c1b98b87458662de44a517d6ad83a9ce4db2fc48d138bfce3588f7 + 015-slinky-slurm-operator-crds/upstream.env: 4d0a2be7546b7bf8bc9469de1609fdaca2af94c51f77882e050878f5820e2b88 015-slinky-slurm-operator-crds/values.yaml: f6ded79ccc11132cec0b9dbbf1248ba5862248b9e4daea35c21e60e28c078b12 016-slinky-slurm-operator/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-slinky-slurm-operator/install.sh: 01a221b08c6dc5193b45aa8a1806e6962960068b181d14d10d04675b4c3621d9 - 016-slinky-slurm-operator/upstream.env: 26b9cd7773cbf321f6fb36fc6011219ef44eacffd2595522466b74807499eb02 + 016-slinky-slurm-operator/upstream.env: f359e532717f31dece6765590458939931c5fe6cfeea774c9441ad360036ec54 016-slinky-slurm-operator/values.yaml: d40d9941ddd05279343fad2c98b2f3c8ac5cb2e2459266e63d1937adab908e60 - 017-slinky-slurm-pre/Chart.yaml: fec67bce3bf4db7adc7a031a87ca73d7e6230715ef4a2f88ca38e7c8a6439a67 + 017-slinky-slurm-pre/Chart.yaml: f65c7669d78ddb55eeccb55768259568f88ceb23bc0853a325ebdefbab18a6a0 017-slinky-slurm-pre/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-slinky-slurm-pre/install.sh: 81a42ad3d2342f567074c56e5e18a07b665ff8eb934c12ae91594ab2c4abb4e3 017-slinky-slurm-pre/templates/enroot-config.yaml: c90815614101b5b1299602c1a89863bb31e98c16e219a9d3e6497f321e140954 017-slinky-slurm-pre/values.yaml: 5643ef72841c8424adbe75cfb40f99691ec60c5e6498bb3a115824a3264bce9d 018-slinky-slurm/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 018-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb - 018-slinky-slurm/upstream.env: ae0598bf066c26ec0f76503212f4c50dc09103750aa36700e514fcfcbaad8c30 + 018-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 018-slinky-slurm/values.yaml: 5643ef72841c8424adbe75cfb40f99691ec60c5e6498bb3a115824a3264bce9d - README.md: 7a2c2b2631c320f17839dc9f06dc5a1b206e05619ed84c151b08079b848d9d7e + README.md: ba0b430277109b5233ae3840444a9476be08c6fc81e2136a02f88e16d5c38b51 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 0365df9937fab0521f97faabb994fd738a5fa3168a29d3cb163f6e78f267c169 - checksums.txt: d5de8542d78559f6e1b286da28e5d26cb80baf3c929725cb441e45f86d009208 + bundle-info.yaml: 1d6e9a4033002d08ff08028039b6afb58544f074a22113d51ae024eeafd06b02 + checksums.txt: aa0d34d3086823fe77e563f649ce4a8699c5530ecb1e783fe4a753b6c771f769 deploy.sh: 3bf1475ef39efa155a2cdff6c99ffeba55d931adf38871f8bc74467845584eae - recipe.yaml: bbbac2a32846177e3d7d9ce205fa12ffb50e95d4556de7651a9540c93eddec9d + recipe.yaml: 62899b14837be9c736a686a2ac9f46a0c32e081991088797e5102dcaa7899b7f h100-gke-cos-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -2870,31 +2870,31 @@ h100-gke-cos-training-slurm: 015-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 016-slinky-slurm-operator-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-slinky-slurm-operator-crds/install.sh: b763afb19a730721e43f3a5be956d4ff183eb0623c8e3c168544ad26e8fbb46f - 016-slinky-slurm-operator-crds/upstream.env: 1c777d58b5c1b98b87458662de44a517d6ad83a9ce4db2fc48d138bfce3588f7 + 016-slinky-slurm-operator-crds/upstream.env: 4d0a2be7546b7bf8bc9469de1609fdaca2af94c51f77882e050878f5820e2b88 016-slinky-slurm-operator-crds/values.yaml: f6ded79ccc11132cec0b9dbbf1248ba5862248b9e4daea35c21e60e28c078b12 017-slinky-slurm-operator/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-slinky-slurm-operator/install.sh: 01a221b08c6dc5193b45aa8a1806e6962960068b181d14d10d04675b4c3621d9 - 017-slinky-slurm-operator/upstream.env: 26b9cd7773cbf321f6fb36fc6011219ef44eacffd2595522466b74807499eb02 + 017-slinky-slurm-operator/upstream.env: f359e532717f31dece6765590458939931c5fe6cfeea774c9441ad360036ec54 017-slinky-slurm-operator/values.yaml: d40d9941ddd05279343fad2c98b2f3c8ac5cb2e2459266e63d1937adab908e60 - 018-slinky-slurm-pre/Chart.yaml: fec67bce3bf4db7adc7a031a87ca73d7e6230715ef4a2f88ca38e7c8a6439a67 + 018-slinky-slurm-pre/Chart.yaml: f65c7669d78ddb55eeccb55768259568f88ceb23bc0853a325ebdefbab18a6a0 018-slinky-slurm-pre/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 018-slinky-slurm-pre/install.sh: 81a42ad3d2342f567074c56e5e18a07b665ff8eb934c12ae91594ab2c4abb4e3 018-slinky-slurm-pre/templates/enroot-config.yaml: c90815614101b5b1299602c1a89863bb31e98c16e219a9d3e6497f321e140954 018-slinky-slurm-pre/values.yaml: d241dedebe0614319d35c94c97e9ed81b2967738139173658a297d0bf696a026 019-slinky-slurm/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 019-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb - 019-slinky-slurm/upstream.env: ae0598bf066c26ec0f76503212f4c50dc09103750aa36700e514fcfcbaad8c30 + 019-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 019-slinky-slurm/values.yaml: d241dedebe0614319d35c94c97e9ed81b2967738139173658a297d0bf696a026 020-slinky-topograph/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 020-slinky-topograph/install.sh: 19c15d32f7578504e561768affa18c21390db951c791a33998fd2bab58a881d8 020-slinky-topograph/upstream.env: 1b99e05b70b8b6b7dd457a99b2e29f9eec8b6244d1854aed0c416ea19a3e62af 020-slinky-topograph/values.yaml: 433c88d6355bfefd023c111e008a39e7c07c913401708a2641717ca5a796a1dd - README.md: 9ffec06121fc2e14304bef09888c1c94eba7c70d3b696eb31013fb412cde9ff1 + README.md: 03fc04c4998661811fa2919d7768f96e45d24b49de8d11c96dc510b4a9e473c9 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 190a095cad5a8cfe43281912e3fce8c35f85097ae4044e773786f0fd06b49be2 - checksums.txt: 4107477a4145b228017a21aa15c12cd82b3145ca19730c1fd76bf9b003eb60c9 + bundle-info.yaml: 30af4e250d05af785988a972fef49aad9a0446dd77385186509eab23c56cc60e + checksums.txt: bf72d8ebad6fb65d350a92a6e6f035e080920ac25152db81fc4b440b54ffb4a8 deploy.sh: 26b5bbeba08ab0830741d513d86fb9b24a204d48968b95c88fb5eadc9fe67cba - recipe.yaml: 31cac72b5e159b01f9bb6a69e53189e9a3c743c6ed55b168884cc7637eb8d3ff + recipe.yaml: cba343a404f486044d2210e877768fefe4126b9a17f9322fa5a396c13efc8f3f h100-kind-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -3095,31 +3095,31 @@ h100-kind-training-slurm: 012-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 013-slinky-slurm-operator-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-slinky-slurm-operator-crds/install.sh: b763afb19a730721e43f3a5be956d4ff183eb0623c8e3c168544ad26e8fbb46f - 013-slinky-slurm-operator-crds/upstream.env: 1c777d58b5c1b98b87458662de44a517d6ad83a9ce4db2fc48d138bfce3588f7 + 013-slinky-slurm-operator-crds/upstream.env: 4d0a2be7546b7bf8bc9469de1609fdaca2af94c51f77882e050878f5820e2b88 013-slinky-slurm-operator-crds/values.yaml: f6ded79ccc11132cec0b9dbbf1248ba5862248b9e4daea35c21e60e28c078b12 014-slinky-slurm-operator/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 014-slinky-slurm-operator/install.sh: 01a221b08c6dc5193b45aa8a1806e6962960068b181d14d10d04675b4c3621d9 - 014-slinky-slurm-operator/upstream.env: 26b9cd7773cbf321f6fb36fc6011219ef44eacffd2595522466b74807499eb02 + 014-slinky-slurm-operator/upstream.env: f359e532717f31dece6765590458939931c5fe6cfeea774c9441ad360036ec54 014-slinky-slurm-operator/values.yaml: d40d9941ddd05279343fad2c98b2f3c8ac5cb2e2459266e63d1937adab908e60 - 015-slinky-slurm-pre/Chart.yaml: fec67bce3bf4db7adc7a031a87ca73d7e6230715ef4a2f88ca38e7c8a6439a67 + 015-slinky-slurm-pre/Chart.yaml: f65c7669d78ddb55eeccb55768259568f88ceb23bc0853a325ebdefbab18a6a0 015-slinky-slurm-pre/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 015-slinky-slurm-pre/install.sh: 81a42ad3d2342f567074c56e5e18a07b665ff8eb934c12ae91594ab2c4abb4e3 015-slinky-slurm-pre/templates/enroot-config.yaml: c90815614101b5b1299602c1a89863bb31e98c16e219a9d3e6497f321e140954 015-slinky-slurm-pre/values.yaml: 3437013a830e817f14f65f7e6dc75729beff0ab88b1ce008867aa464d066a514 016-slinky-slurm/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb - 016-slinky-slurm/upstream.env: ae0598bf066c26ec0f76503212f4c50dc09103750aa36700e514fcfcbaad8c30 + 016-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 016-slinky-slurm/values.yaml: 3437013a830e817f14f65f7e6dc75729beff0ab88b1ce008867aa464d066a514 017-slinky-topograph/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-slinky-topograph/install.sh: 19c15d32f7578504e561768affa18c21390db951c791a33998fd2bab58a881d8 017-slinky-topograph/upstream.env: 1b99e05b70b8b6b7dd457a99b2e29f9eec8b6244d1854aed0c416ea19a3e62af 017-slinky-topograph/values.yaml: 8cc3bf52dbab729d1b71e495c8d51a58a5ea3592b18b356e4bbc0ff7b587b188 - README.md: 9e75e15c8f365e9420fa72d715062ee018329edd610099734138753fa2c23146 + README.md: 21af7eb79c1e695598de534bae5ec18d2de26cb05c16c8985db30914eb5481d4 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: a93cb191edf0c4e9a18dbf165832a44a2e6bddb9dcb3a724ca21741884347fb0 - checksums.txt: 1bd46eb553298268a254522feb66ad2761a31339363457422ebe562fa9637ec8 + bundle-info.yaml: 8cb46afe6f9e348a13c912c81120765c9510bb9e4938243ea8886cff7200d681 + checksums.txt: e1bd82aea341646f0114de57f92b30ff78a98e636389a5c2272669c84da8c5aa deploy.sh: a9268f292354d1038ae6c7401d39c2fd190aafd3e2f0f7a3820ee740e685255b - recipe.yaml: 385bac65d13d3a64c7de7f8f300fe0d6811914d2e65206072d3bf8606d642fc5 + recipe.yaml: 786ff5028c4d02ebf8d5fdb9a3f5f8078196fa63136306c0e8ec93f6bb9e0cc3 h200-any: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd diff --git a/pkg/recipe/components_test.go b/pkg/recipe/components_test.go index c4385febae..df9d93fb2f 100644 --- a/pkg/recipe/components_test.go +++ b/pkg/recipe/components_test.go @@ -398,7 +398,7 @@ func TestComponentRegistry_SlinkySlurmChartVersions(t *testing.T) { t.Fatalf("failed to load component registry: %v", err) } - const wantVersion = "1.2.0" + const wantVersion = "1.2.2" for _, name := range []string{ "slinky-slurm-operator-crds", "slinky-slurm-operator", diff --git a/pkg/recipe/testdata/catalog_parity_golden.yaml b/pkg/recipe/testdata/catalog_parity_golden.yaml index b38204e5ec..c8e2f4b16b 100644 --- a/pkg/recipe/testdata/catalog_parity_golden.yaml +++ b/pkg/recipe/testdata/catalog_parity_golden.yaml @@ -17,32 +17,32 @@ eks-ubuntu: bc8d2ac072df16e990ecf76ceb60bfd0be8dc854867d9b2fbd9c5daf05c215f8 gb200-any: f886178cf74ec415ec2e95e9a32f2b8c41416684a62ef5cbe277288c14699c1f gb200-eks-ubuntu-inference-dynamo: 7c205fbad4c98c153b1b2b8784a975959787e19aa3ce616fdccb0bec97ce4b80 gb200-eks-ubuntu-training-kubeflow: b1590df9addcc3ff3386e0a2d25e658396731f67b320573008d3426ead84c2a4 -gb200-eks-ubuntu-training-slurm: 3e165ff6980c45b1719201e405fd326ea09dfc527bcb22881ed6b55734452cb6 +gb200-eks-ubuntu-training-slurm: 198b2414e175714405bf75d9e4e6e7e7ce637010afead9c9b46fe7755f730d23 gb200-gke-cos-inference-dynamo: 20400798cbb2c9e65265a88e9e72a898f8b132fc044b92e0c915f2169e89512a gb200-gke-cos-training-kubeflow: 77064b09640222b09ea169f2c7064797224c2121d2a184c90796651613305112 -gb200-gke-cos-training-slurm: 2d8c52cfd8d865fa93dc7227bc5e76ac1f8f296a2123c3d82495a16251627a18 +gb200-gke-cos-training-slurm: 40eae7f750e60be3d80f671ac8986dd22d2a37d88d78aa748765bbe4d843d229 gb200-oke-ubuntu-inference-dynamo: 4166375b2e48875a7ee2a4bf7c6b45762367d3d5ee2a4d326a97c44533a76ffa gb200-oke-ubuntu-training-kubeflow: ff62cde41872e5fb9c52c97d2094a7952e5d514970a753e91b815fa66f0c90a6 gb300-any: 96aa04360e1f10f8b42e5bd1f918d558d41339cb002bf515ef6dac53f3c9bd5f gb300-eks-ubuntu-inference-dynamo: 2b3d513ba6f063648b7bcf3e38ac3e9c236be8328f8cdbb5599cc668c3ab66a0 gb300-eks-ubuntu-training-kubeflow: 8874fdf7b8060fca11f7412e2c7090d0869c068ad5d352be7b4c7957f52ab311 -gb300-eks-ubuntu-training-slurm: 9e41edc5da160ece226496f8cdda156f84787816342b189cfced01f4c2fd7dc8 +gb300-eks-ubuntu-training-slurm: 5e455dc0f1413fa89af66fea01d2cf44cd7a8d8a94d627642f3fc0fdb0cbb204 gb300-generic-ubuntu-training: 8cd1c26e2d7b9d7f0605695fbb32d98f5204e282b7b0e52473f40b9761287bdf h100-aks-ubuntu-inference-dynamo: 54ad5bcf3ecf22ade1720091d8ab3a260ecb7b0784824417c1d77683693e6d5f h100-aks-ubuntu-training-kubeflow: 9936cf1a5dce954f41c2076ba1bcaa1e029e19bee4d0660e07fc39e08b682a15 -h100-aks-ubuntu-training-slurm: 2e6ec6b09507943ae5475de0de7cbac7b4f7ec84874431a8845626101cbb24b4 +h100-aks-ubuntu-training-slurm: 549d04fb2e37ea5114f156cc023b7a43290d4408e254ee1406350cf681a24172 h100-any: 902ee0497cc4358441c42f533f01438be066b318def504eaf30859fd8f9b90d2 h100-bcm-ubuntu-training-kubeflow: 7e850295309d0dfb6a65b990a52b69fd3a892a352b846a909e956b41e2485c18 h100-eks-ubuntu-inference-dynamo: b5c1edc0859c57fcbbf8a429312f1ccc225793c28774405b6692550aaa81b50e h100-eks-ubuntu-inference-nim: eed32e85aa44bd0734aefaf7214866db7a80d28711d65bb423d47ea4c1113862 h100-eks-ubuntu-training-kubeflow: 03990c0bf9544f1914f55fdb57a53b4dd2214fa922244994b8cfce538f3d143a -h100-eks-ubuntu-training-slurm: 11857e5794c1bfede7d93a6483b7e5f880dba8610474e11e824affc4d0cc3892 +h100-eks-ubuntu-training-slurm: bebb2896b7b96a8ee8a7516a7c1927f1bfd4fb6e8cbf39e09e2c84b817e7e714 h100-gke-cos-inference-dynamo: 3392baf8b9bcec9eb7d3cfe5d316dd9d32b1f4277e700c29c1b67c65efb8eb9d h100-gke-cos-training-kubeflow: 16c3fe5d2f954caadba58a3d319acfd2db229ed4f0474d78ac30157483e2c5e0 -h100-gke-cos-training-slurm: 27846c06230f94718ec0054a3b06b9f3fd7e8783645478be3f2e465a3ac8abde +h100-gke-cos-training-slurm: 9b65fce98a83148a2e5cc7eecb86f421ae57ea578ad42b27b4359119b0259621 h100-kind-inference-dynamo: 5552082356c8339d3c54ee6e275659e690913c138448dd1f5e1eb4a6e9703a5d h100-kind-training-kubeflow: 52bc7adcf5b36ec774eb1d5212f63eea9a4253130ce6d1b6d80199d123115d01 -h100-kind-training-slurm: ca8fdd35cae361188d96681cfaa9e2e9c6bb087185ca64b7b79321bde2be3f1d +h100-kind-training-slurm: 99732b44a1c3f0d749612f581dd9daf8843473a98f637296bb9bd15104b50ed4 h200-any: c560a926b1997210654edee1d2d299f59ca7bd58d7ae11679b4649ea63b095dd h200-eks-inference: e8108add208b99f58fb9c9f49da13a9a149509075ec730db580b52201e67b1a1 h200-eks-training-kubeflow: 4beaaf1f420c840b42d50b29595013f0cf8674ff4963ff75f9cdbe96805cd66c diff --git a/recipes/checks/kueue/health-check.yaml b/recipes/checks/kueue/health-check.yaml index 5c5265bc19..539a3745a9 100644 --- a/recipes/checks/kueue/health-check.yaml +++ b/recipes/checks/kueue/health-check.yaml @@ -17,7 +17,7 @@ # Validates that Kueue is running and healthy in the kueue-system # namespace. Asserts resourceflavors / clusterqueues / # localqueues.kueue.x-k8s.io are Established=True (verified against -# chart 0.19.3; re-verify on defaultVersion bump), and that the default +# chart 0.19.5; re-verify on defaultVersion bump), and that the default # quota CRs shipped with the component (ResourceFlavor default-flavor, # ClusterQueue cluster-queue, LocalQueue default/default) were admitted # and reconciled to Active — a functional proof (CRDs installed, @@ -138,7 +138,7 @@ spec: try: # The default quota CRs ship with the component via registry # manifestFiles (wave N+1), so they must exist wherever this - # check runs. v1beta2 is the storage version in chart 0.19.3. + # check runs. v1beta2 is the storage version in chart 0.19.5. # # COUPLING: these asserts are pinned to the DEFAULT CR names. An # overlay that overrides the component's manifestFiles (shipping diff --git a/recipes/checks/slinky-slurm-operator-crds/health-check.yaml b/recipes/checks/slinky-slurm-operator-crds/health-check.yaml index 4e58f49e67..7da18685ca 100644 --- a/recipes/checks/slinky-slurm-operator-crds/health-check.yaml +++ b/recipes/checks/slinky-slurm-operator-crds/health-check.yaml @@ -19,7 +19,7 @@ # apiserver will accept CRs of those kinds). # # CRDs come from the upstream SchedMD Slinky slurm-operator-crds chart -# pinned to 1.1.0 (oci://ghcr.io/slinkyproject/charts) in +# pinned to 1.2.2 (oci://ghcr.io/slinkyproject/charts) in # recipes/registry.yaml. The 6 kinds under slinky.slurm.net are # enumerated in recipes/components/slinky-slurm-operator-crds/values.yaml # header: Accounting, Controller, LoginSet, NodeSet, RestApi, Token. diff --git a/recipes/components/kueue/values.yaml b/recipes/components/kueue/values.yaml index fff298d9f7..3e3818b925 100644 --- a/recipes/components/kueue/values.yaml +++ b/recipes/components/kueue/values.yaml @@ -24,7 +24,7 @@ controllerManager: tolerations: - operator: Exists -# Pinned copy of the chart 0.19.3 default controllerManagerConfigYaml with +# Pinned copy of the chart 0.19.5 default controllerManagerConfigYaml with # ONE deliberate change: integrations.frameworks is trimmed to the # frameworks AICR manages (batch/job, JobSet, TrainJob). The chart default # also enables mpijob/ray (rayjob, rayservice, raycluster)/appwrapper/pod/ diff --git a/recipes/components/slinky-slurm-operator/values.yaml b/recipes/components/slinky-slurm-operator/values.yaml index 56d814a6b2..06435603f6 100644 --- a/recipes/components/slinky-slurm-operator/values.yaml +++ b/recipes/components/slinky-slurm-operator/values.yaml @@ -12,7 +12,7 @@ # See the License for the specific language governing permissions and # limitations under the License. -# Slinky Slurm Operator Helm values (chart v1.2.0) +# Slinky Slurm Operator Helm values (chart v1.2.2) # Deploys the SchedMD Slinky Slurm operator and its admission webhook into # the `slinky` namespace. Manages the lifecycle of Slurm clusters declared # via the Controller / NodeSet / LoginSet / Accounting / RestApi / Token diff --git a/recipes/registry.yaml b/recipes/registry.yaml index cad6459e3f..a45ac910d4 100644 --- a/recipes/registry.yaml +++ b/recipes/registry.yaml @@ -958,7 +958,7 @@ components: defaultRepository: oci://registry.k8s.io/kueue/charts defaultChart: kueue # renovate: datasource=docker depName=registry.k8s.io/kueue/charts/kueue - defaultVersion: "0.19.3" + defaultVersion: "0.19.5" defaultNamespace: kueue-system nodeScheduling: system: @@ -1122,7 +1122,7 @@ components: defaultRepository: oci://ghcr.io/slinkyproject/charts defaultChart: slurm-operator-crds # renovate: datasource=docker depName=ghcr.io/slinkyproject/charts/slurm-operator-crds - defaultVersion: "1.2.0" + defaultVersion: "1.2.2" defaultNamespace: slinky - name: mariadb-operator-crds @@ -1217,7 +1217,7 @@ components: # file mirrors the chart defaults explicitly for documentation, but # an upstream default flip would otherwise pass through unnoticed. # renovate: datasource=docker depName=ghcr.io/slinkyproject/charts/slurm-operator - defaultVersion: "1.2.0" + defaultVersion: "1.2.2" defaultNamespace: slinky nodeScheduling: system: @@ -1246,7 +1246,7 @@ components: # pkg/recipe TestComponentRegistry_SlinkySlurm_NodeSchedulingPaths # enforces their alignment with the scheduling paths below. # renovate: datasource=docker depName=ghcr.io/slinkyproject/charts/slurm - defaultVersion: "1.2.0" + defaultVersion: "1.2.2" defaultNamespace: slurm sharedStorageClassPaths: - storage.home.storageClassName From 3cea372e827a9999ec2c0cfb10de77d140aaa51f Mon Sep 17 00:00:00 2001 From: Carlos Eduardo Arango Gutierrez Date: Mon, 28 Sep 2026 16:05:30 +0200 Subject: [PATCH 2/9] chore(recipes): bump kueue to 0.19.6 The 2026-09-28 drift report moved kueue past this PR's 0.19.5 pin. The chart's controllerManagerConfigYaml changed this time, so the pinned copy in recipes/components/kueue/values.yaml is re-diffed and re-synced: 0.19.6 adds `Cohort.kueue.x-k8s.io: 1` to controller.groupKindConcurrency (kueue #15876, which syncs the Helm blob with the kustomize config). The line is adopted so AICR's copy still differs from the chart default by exactly the integrations.frameworks trim, and nothing else. It does not change behavior: the Cohort reconciler reads its concurrency from that map, an absent key yields 0, and controller-runtime v0.24.1 (kueue's pin) raises 0 to 1. Other rendered changes against AICR's values: twelve new ClusterRoles, editor and viewer for admissionchecks, appwrappers, multikueueclusters, multikueueconfigs, provisioningrequestconfigs and workloadpriorityclasses (kueue #16032, #16101). All carry rbac.kueue.x-k8s.io/batch-admin and aggregate into kueue-batch-admin-role, which the chart binds to no subject. The viewer roles also aggregate into the built-in admin ClusterRole (the appwrapper viewer into view and edit too), so subjects already bound to admin gain read on those kinds. kueue-manager-role is unchanged. The CRD templates are byte-identical to 0.19.5 and v1beta2 stays the storage version for resourceflavors, clusterqueues and localqueues, so the health check and the three bundled quota manifests keep their apiVersion. The health check's CRD step comment still named chart 0.19.3; it now names the current pin. Release-note review of the two "Actions Required" items in 0.19.6: - DRA quota accounting now subtracts only the containers' own request, so chargeable Pod overhead or a resource-transformation output that shares a name with a DRA-backed extended resource stays counted, and usage on that name can rise. A default AICR install does not reach this path. The pinned kueue config sets no resources.transformations, deviceClassMappings or excludeResourcePrefixes (the only matches under recipes/components/kueue are the chart's commented-out example), and no overlay or mixin references kueue. nvidia-dra-driver-gpu ships with resources.gpus.enabled=false, so its gpu.nvidia.com DeviceClass, the only one in chart 0.5.0 that declares an extendedResourceName (nvidia.com/gpu), is not rendered, and no overlay turns it on. The bundled ClusterQueue holds 100000 nvidia.com/gpu of nominal quota, so a rise could not change admission against it either. The change reaches only a cluster that enabled the DRA full-GPU DeviceClass through an override and also has Pod overhead or a transformation output under that name. - SparkApplication now reserves cores and memory overhead. Inert here: the integration is commented out in the chart default and AICR's frameworks trim does not add it. The kueue section of docs/user/component-catalog.md does cover override-reachable changes, but both items need an opt-in AICR does not ship, and upstream's note already carries the operator actions, so no 0.19.6 note is added there. make bom-docs moves the kueue row and image to 0.19.6 and nothing else. make update-goldens produces no change, because kueue is in no stock leaf. No ADR-021 record: kueue has none, and this bump moves no CRD, API or storage version, and no values path. Signed-off-by: Carlos Eduardo Arango Gutierrez --- docs/user/container-images.md | 4 ++-- recipes/checks/kueue/health-check.yaml | 6 +++--- recipes/components/kueue/values.yaml | 3 ++- recipes/registry.yaml | 2 +- 4 files changed, 8 insertions(+), 7 deletions(-) diff --git a/docs/user/container-images.md b/docs/user/container-images.md index 7e02805c77..33696acd56 100644 --- a/docs/user/container-images.md +++ b/docs/user/container-images.md @@ -56,7 +56,7 @@ _Rendering fidelity:_ `catalog-parity: charts are rendered with the shared recip | kai-scheduler | helm | kai-scheduler | v0.16.9 | 12 | | kube-prometheus-stack | helm | prometheus-community/kube-prometheus-stack | 84.4.0 | 8 | | kubeflow-trainer | helm | kubeflow-trainer | 2.2.0 | 4 | -| kueue | helm | kueue | 0.19.5 | 1 | +| kueue | helm | kueue | 0.19.6 | 1 | | mariadb-operator | helm | mariadb-operator | 26.6.0 | 1 | | mariadb-operator-crds | helm | mariadb-operator-crds | 26.6.0 | 0 | | network-operator | helm | nvidia/network-operator | 26.4.1 | 12 | @@ -245,7 +245,7 @@ _No images extracted._ ### kueue -- `registry.k8s.io/kueue/kueue:v0.19.5` +- `registry.k8s.io/kueue/kueue:v0.19.6` ### mariadb-operator diff --git a/recipes/checks/kueue/health-check.yaml b/recipes/checks/kueue/health-check.yaml index 539a3745a9..4451bde30c 100644 --- a/recipes/checks/kueue/health-check.yaml +++ b/recipes/checks/kueue/health-check.yaml @@ -17,7 +17,7 @@ # Validates that Kueue is running and healthy in the kueue-system # namespace. Asserts resourceflavors / clusterqueues / # localqueues.kueue.x-k8s.io are Established=True (verified against -# chart 0.19.5; re-verify on defaultVersion bump), and that the default +# chart 0.19.6; re-verify on defaultVersion bump), and that the default # quota CRs shipped with the component (ResourceFlavor default-flavor, # ClusterQueue cluster-queue, LocalQueue default/default) were admitted # and reconciled to Active — a functional proof (CRDs installed, @@ -36,7 +36,7 @@ spec: # kueue.x-k8s.io group verified in-tree: the manifests this # component ships (recipes/components/kueue/manifests/*.yaml) # use apiVersion kueue.x-k8s.io/v1beta2 for ResourceFlavor, - # ClusterQueue, and LocalQueue. Chart 0.19.3 (recipes/registry.yaml). + # ClusterQueue, and LocalQueue. Chart 0.19.6 (recipes/registry.yaml). - assert: resource: apiVersion: apiextensions.k8s.io/v1 @@ -138,7 +138,7 @@ spec: try: # The default quota CRs ship with the component via registry # manifestFiles (wave N+1), so they must exist wherever this - # check runs. v1beta2 is the storage version in chart 0.19.5. + # check runs. v1beta2 is the storage version in chart 0.19.6. # # COUPLING: these asserts are pinned to the DEFAULT CR names. An # overlay that overrides the component's manifestFiles (shipping diff --git a/recipes/components/kueue/values.yaml b/recipes/components/kueue/values.yaml index 3e3818b925..f6ffb18459 100644 --- a/recipes/components/kueue/values.yaml +++ b/recipes/components/kueue/values.yaml @@ -24,7 +24,7 @@ controllerManager: tolerations: - operator: Exists -# Pinned copy of the chart 0.19.5 default controllerManagerConfigYaml with +# Pinned copy of the chart 0.19.6 default controllerManagerConfigYaml with # ONE deliberate change: integrations.frameworks is trimmed to the # frameworks AICR manages (batch/job, JobSet, TrainJob). The chart default # also enables mpijob/ray (rayjob, rayservice, raycluster)/appwrapper/pod/ @@ -71,6 +71,7 @@ managerConfig: Pod: 5 Workload.kueue.x-k8s.io: 10 LocalQueue.kueue.x-k8s.io: 5 + Cohort.kueue.x-k8s.io: 1 ClusterQueue.kueue.x-k8s.io: 5 ResourceFlavor.kueue.x-k8s.io: 1 clientConnection: diff --git a/recipes/registry.yaml b/recipes/registry.yaml index a45ac910d4..6361fa965e 100644 --- a/recipes/registry.yaml +++ b/recipes/registry.yaml @@ -958,7 +958,7 @@ components: defaultRepository: oci://registry.k8s.io/kueue/charts defaultChart: kueue # renovate: datasource=docker depName=registry.k8s.io/kueue/charts/kueue - defaultVersion: "0.19.5" + defaultVersion: "0.19.6" defaultNamespace: kueue-system nodeScheduling: system: From 077a215073080e6b03bce12e032b58482842c7c3 Mon Sep 17 00:00:00 2001 From: Carlos Eduardo Arango Gutierrez Date: Mon, 21 Sep 2026 11:34:57 +0200 Subject: [PATCH 3/9] chore(recipes): bump MariaDB charts to 26.10.0, pin engine image The three MariaDB pins from the 2026-09-21 drift report, moved together: mariadb-operator-crds, mariadb-operator and slurm-accounting-mariadb (chart mariadb-cluster) all go 26.6.0 -> 26.10.0. Upstream uses CalVer, so despite the minor-looking jump the only 26.x releases are 26.3.0, 26.6.0 and 26.10.0; this is a single release, not four. The chart surface is quiet. Rendered under AICR's own values the MariaDB resource is byte-identical apart from the helm.sh/chart label, every consumed values path still resolves, and the CRD delta is five optional fields plus three enum widenings with no removals, no new required fields and no stored-version change. The slurmdbd wiring that makes accounting work at all (Service mariadb, Secret mariadb-password key password, database slurm_acct_db, user slurm) was checked against the 26.10.0 render and holds. Two things in this release are not visible in the chart diff. The operator's default server image moves from mariadb:11.8.8 to mariadb:12.3.3, a MariaDB major version. AICR never pinned spec.image, so existing clusters would keep 11.8.8 while any newly bundled slurm_acct_db came up on 12.3.3, and slurmdbd's supported MariaDB matrix has not been checked against 12.3. This pins mariadb:11.8.8 explicitly, which keeps fresh and standing clusters on one engine and makes the version an AICR decision rather than a side effect of an operator bump. It also closes a BOM blind spot: the operator's default lives in its runtime config block where a render-based BOM cannot see it, so slurm-accounting-mariadb previously reported no images at all and now reports mariadb:11.8.8. Moving to 12.3 is its own change, with its own UAT. Upstream also requires updateStrategy.autoUpdateDataPlane=true on every MariaDB before the operator upgrade, reverted afterwards, because the release changes the replication config rendered by the init container and the agent's replication liveness probe. That is an upgrade-window procedure, not standing configuration, so it lands as an ADR-021 manual record rather than a values key: baking true into values would contradict upstream's own revert guidance and silently update the data plane on every later operator bump. The record is manual and carries no verifiedBy, because no KWOK or UAT lane has exercised this transition and a wrong safe is worse than no record. Its from domain opens below the pin so no earlier operator version matches nothing. The gate was mutation-checked: dropping the remainder step group makes check-upgrade-records fail with "manual but has no steps for deployer argocd", and it passes again once restored. Golden parity files were regenerated with AICR_UPDATE_GOLDEN=1; the diff touches exactly the seven *-training-slurm leaves and no other leaf. Signed-off-by: Carlos Eduardo Arango Gutierrez --- docs/user/component-catalog.md | 40 ++++++ docs/user/container-images.md | 12 +- .../testdata/catalog_parity_golden.yaml | 14 +- .../components/mariadb-operator/upgrades.yaml | 120 ++++++++++++++++++ .../slurm-accounting-mariadb/values.yaml | 9 ++ recipes/registry.yaml | 8 +- 6 files changed, 187 insertions(+), 16 deletions(-) create mode 100644 recipes/components/mariadb-operator/upgrades.yaml diff --git a/docs/user/component-catalog.md b/docs/user/component-catalog.md index afbdc7e1ab..6554fd9ded 100644 --- a/docs/user/component-catalog.md +++ b/docs/user/component-catalog.md @@ -1555,6 +1555,46 @@ also installs `computedomains` from its chart. This pairing has not yet been verified on a live OpenShift cluster; see [NVIDIA/aicr#2969](https://github.com/NVIDIA/aicr/issues/2969). +### `mariadb-operator`: `26.6.0` (or earlier) to `26.10.0` + +`26.10.0` changes the replication configuration rendered by the MariaDB init +container and the replication liveness probe served by the agent, so the data +plane has to move with the operator. `updateStrategy.autoUpdateDataPlane` +defaults to `false`, so an operator upgraded without setting it first runs +`26.10.0` against init and agent containers left at the prior version. + +Fresh installs are unaffected. To migrate an existing cluster, set the flag +**before** the operator moves, then upgrade CRDs first and the operator second: + +1. Enable data-plane auto-update on every MariaDB the operator manages (AICR's + accounting database is `mariadb` in namespace `slurm`): + ```bash + kubectl patch mariadb mariadb -n slurm --type merge \ + -p '{"spec":{"updateStrategy":{"autoUpdateDataPlane":true}}}' + ``` +2. Upgrade `mariadb-operator-crds` to `26.10.0` **in place**. Never + `helm uninstall` the CRD chart: that deletes the CRDs and cascade-deletes + every `MariaDB`, `User`, `Database` and `Grant` with them. +3. Upgrade `mariadb-operator` to `26.10.0` (re-run `install.sh`, `helmfile + apply`, or sync the release). +4. Return the flag to `false` so a later operator bump does not update the data + plane unattended. If the field is managed in git, set it there. + +The same release changes the operator's default server image to +`mariadb:12.3.3`. AICR pins `mariadb:11.8.8` in +`recipes/components/slurm-accounting-mariadb/values.yaml`, so a cluster bundled +from this recipe stays on `11.8.8`; the pin also puts the server image into the +rendered `MariaDB` resource, where the BOM records it. Any `MariaDB` that omits +`spec.image` takes the operator default and will move to a new MariaDB major +version on its next reconcile. Check with: + +```bash +kubectl get mariadb -A \ + -o custom-columns=NS:.metadata.namespace,NAME:.metadata.name,IMAGE:.spec.image +``` + +A blank `IMAGE` column means that cluster takes the default. + ### `agentgateway`: upgrading across breaking releases AICR pins the `agentgateway` and `agentgateway-crds` charts in the component diff --git a/docs/user/container-images.md b/docs/user/container-images.md index 33696acd56..beaf11453a 100644 --- a/docs/user/container-images.md +++ b/docs/user/container-images.md @@ -20,7 +20,7 @@ A machine-readable **CycloneDX 1.6 JSON** companion to this page is produced by ## Summary - Components: **49** -- Unique images: **113** +- Unique images: **114** - Distinct registries: **11** Registries: `602401143452.dkr.ecr.us-west-2.amazonaws.com`, `cr.agentgateway.dev`, `docker.io`, `gcr.io`, `ghcr.io`, `gke.gcr.io`, `nvcr.io`, `public.ecr.aws`, `quay.io`, `registry.k8s.io`, `us-docker.pkg.dev` @@ -57,8 +57,8 @@ _Rendering fidelity:_ `catalog-parity: charts are rendered with the shared recip | kube-prometheus-stack | helm | prometheus-community/kube-prometheus-stack | 84.4.0 | 8 | | kubeflow-trainer | helm | kubeflow-trainer | 2.2.0 | 4 | | kueue | helm | kueue | 0.19.6 | 1 | -| mariadb-operator | helm | mariadb-operator | 26.6.0 | 1 | -| mariadb-operator-crds | helm | mariadb-operator-crds | 26.6.0 | 0 | +| mariadb-operator | helm | mariadb-operator | 26.10.0 | 1 | +| mariadb-operator-crds | helm | mariadb-operator-crds | 26.10.0 | 0 | | network-operator | helm | nvidia/network-operator | 26.4.1 | 12 | | network-operator-ocp | manifest | — | — | 0 | | network-operator-ocp-olm | manifest | — | — | 0 | @@ -79,7 +79,7 @@ _Rendering fidelity:_ `catalog-parity: charts are rendered with the shared recip | slinky-slurm-operator | helm | slurm-operator | 1.2.2 | 2 | | slinky-slurm-operator-crds | helm | slurm-operator-crds | 1.2.2 | 0 | | slinky-topograph | helm | topograph/topograph | 1.0.0 | 1 | -| slurm-accounting-mariadb | helm | mariadb-cluster | 26.6.0 | 0 | +| slurm-accounting-mariadb | helm | mariadb-cluster | 26.10.0 | 1 | ## Version variants @@ -249,7 +249,7 @@ _No images extracted._ ### mariadb-operator -- `ghcr.io/mariadb-operator/mariadb-operator:26.6.0` +- `ghcr.io/mariadb-operator/mariadb-operator:26.10.0` ### mariadb-operator-crds @@ -365,7 +365,7 @@ _No images extracted._ ### slurm-accounting-mariadb -_No images extracted._ +- `mariadb:11.8.8` ### kube-prometheus-stack@83.7.0 (variant) diff --git a/pkg/recipe/testdata/catalog_parity_golden.yaml b/pkg/recipe/testdata/catalog_parity_golden.yaml index c8e2f4b16b..b8795ab6ed 100644 --- a/pkg/recipe/testdata/catalog_parity_golden.yaml +++ b/pkg/recipe/testdata/catalog_parity_golden.yaml @@ -17,32 +17,32 @@ eks-ubuntu: bc8d2ac072df16e990ecf76ceb60bfd0be8dc854867d9b2fbd9c5daf05c215f8 gb200-any: f886178cf74ec415ec2e95e9a32f2b8c41416684a62ef5cbe277288c14699c1f gb200-eks-ubuntu-inference-dynamo: 7c205fbad4c98c153b1b2b8784a975959787e19aa3ce616fdccb0bec97ce4b80 gb200-eks-ubuntu-training-kubeflow: b1590df9addcc3ff3386e0a2d25e658396731f67b320573008d3426ead84c2a4 -gb200-eks-ubuntu-training-slurm: 198b2414e175714405bf75d9e4e6e7e7ce637010afead9c9b46fe7755f730d23 +gb200-eks-ubuntu-training-slurm: 2c9e0ad3004b50ae799026da18a262b95675c7baca96218f15a1bf6fbc2230c5 gb200-gke-cos-inference-dynamo: 20400798cbb2c9e65265a88e9e72a898f8b132fc044b92e0c915f2169e89512a gb200-gke-cos-training-kubeflow: 77064b09640222b09ea169f2c7064797224c2121d2a184c90796651613305112 -gb200-gke-cos-training-slurm: 40eae7f750e60be3d80f671ac8986dd22d2a37d88d78aa748765bbe4d843d229 +gb200-gke-cos-training-slurm: 8dd15a84094e104a8e562da26de003a88493e943b8e5a0d3122e337a1a85d48b gb200-oke-ubuntu-inference-dynamo: 4166375b2e48875a7ee2a4bf7c6b45762367d3d5ee2a4d326a97c44533a76ffa gb200-oke-ubuntu-training-kubeflow: ff62cde41872e5fb9c52c97d2094a7952e5d514970a753e91b815fa66f0c90a6 gb300-any: 96aa04360e1f10f8b42e5bd1f918d558d41339cb002bf515ef6dac53f3c9bd5f gb300-eks-ubuntu-inference-dynamo: 2b3d513ba6f063648b7bcf3e38ac3e9c236be8328f8cdbb5599cc668c3ab66a0 gb300-eks-ubuntu-training-kubeflow: 8874fdf7b8060fca11f7412e2c7090d0869c068ad5d352be7b4c7957f52ab311 -gb300-eks-ubuntu-training-slurm: 5e455dc0f1413fa89af66fea01d2cf44cd7a8d8a94d627642f3fc0fdb0cbb204 +gb300-eks-ubuntu-training-slurm: 70f1bfa28fbbeaa0711d54dbd7c0a265bc5fab392c4ad10cd51528711c0a40d1 gb300-generic-ubuntu-training: 8cd1c26e2d7b9d7f0605695fbb32d98f5204e282b7b0e52473f40b9761287bdf h100-aks-ubuntu-inference-dynamo: 54ad5bcf3ecf22ade1720091d8ab3a260ecb7b0784824417c1d77683693e6d5f h100-aks-ubuntu-training-kubeflow: 9936cf1a5dce954f41c2076ba1bcaa1e029e19bee4d0660e07fc39e08b682a15 -h100-aks-ubuntu-training-slurm: 549d04fb2e37ea5114f156cc023b7a43290d4408e254ee1406350cf681a24172 +h100-aks-ubuntu-training-slurm: 50add28d1ad55791fccfc681901cf4cad9e7d6f0d3885f23258c6b42df47f698 h100-any: 902ee0497cc4358441c42f533f01438be066b318def504eaf30859fd8f9b90d2 h100-bcm-ubuntu-training-kubeflow: 7e850295309d0dfb6a65b990a52b69fd3a892a352b846a909e956b41e2485c18 h100-eks-ubuntu-inference-dynamo: b5c1edc0859c57fcbbf8a429312f1ccc225793c28774405b6692550aaa81b50e h100-eks-ubuntu-inference-nim: eed32e85aa44bd0734aefaf7214866db7a80d28711d65bb423d47ea4c1113862 h100-eks-ubuntu-training-kubeflow: 03990c0bf9544f1914f55fdb57a53b4dd2214fa922244994b8cfce538f3d143a -h100-eks-ubuntu-training-slurm: bebb2896b7b96a8ee8a7516a7c1927f1bfd4fb6e8cbf39e09e2c84b817e7e714 +h100-eks-ubuntu-training-slurm: cf3a6623ffbe0f7feee9a4a22627ef28bf8eb3ad9061a0d02c2f0f28fa2725f2 h100-gke-cos-inference-dynamo: 3392baf8b9bcec9eb7d3cfe5d316dd9d32b1f4277e700c29c1b67c65efb8eb9d h100-gke-cos-training-kubeflow: 16c3fe5d2f954caadba58a3d319acfd2db229ed4f0474d78ac30157483e2c5e0 -h100-gke-cos-training-slurm: 9b65fce98a83148a2e5cc7eecb86f421ae57ea578ad42b27b4359119b0259621 +h100-gke-cos-training-slurm: 5f4598d921663870b38837455252a7ae097888a05fff77be85d462a356ccd17e h100-kind-inference-dynamo: 5552082356c8339d3c54ee6e275659e690913c138448dd1f5e1eb4a6e9703a5d h100-kind-training-kubeflow: 52bc7adcf5b36ec774eb1d5212f63eea9a4253130ce6d1b6d80199d123115d01 -h100-kind-training-slurm: 99732b44a1c3f0d749612f581dd9daf8843473a98f637296bb9bd15104b50ed4 +h100-kind-training-slurm: 44f962318e08558aef36a886abf25d659a3ba46b2d8fcb1e756cb6c87e38fef6 h200-any: c560a926b1997210654edee1d2d299f59ca7bd58d7ae11679b4649ea63b095dd h200-eks-inference: e8108add208b99f58fb9c9f49da13a9a149509075ec730db580b52201e67b1a1 h200-eks-training-kubeflow: 4beaaf1f420c840b42d50b29595013f0cf8674ff4963ff75f9cdbe96805cd66c diff --git a/recipes/components/mariadb-operator/upgrades.yaml b/recipes/components/mariadb-operator/upgrades.yaml new file mode 100644 index 0000000000..c05e1371fd --- /dev/null +++ b/recipes/components/mariadb-operator/upgrades.yaml @@ -0,0 +1,120 @@ +# Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +apiVersion: aicr.run/v1beta1 +kind: ComponentUpgrades +component: mariadb-operator +transitions: + # from opens below the pin rather than at 26.6.0: upstream uses CalVer and + # the only 26.x releases are 26.3.0, 26.6.0 and 26.10.0, so an operator + # arriving from any of them crosses the same boundary. Naming 26.6.0 as the + # floor would leave every earlier pin matching nothing. + # + # verdict is manual, not safe, and carries no verifiedBy: no UAT lane or + # KWOK run has exercised this transition. The procedure below is transcribed + # from upstream's own upgrade guide, not vouched for by a run here. + - from: "<26.10.0" + to: "26.10.0" + verdict: manual + summary: >- + 26.10.0 changes the replication configuration rendered by the MariaDB + init container and the replication liveness probe served by the agent, + so the data plane must move with the operator. autoUpdateDataPlane + defaults to false, so an operator upgraded without setting it first runs + 26.10.0 against init and agent containers left at the prior version. + The release also changes the operator's default server image to + mariadb:12.3.3; AICR pins mariadb:11.8.8 in the slurm-accounting-mariadb + values, so a cluster bundled from this recipe is unaffected, but any + MariaDB CR that omits spec.image will come up on a new MariaDB major + version. + precondition: >- + Know which MariaDB resources the operator manages and whether any omits + spec.image. Check with + `kubectl get mariadb -A -o custom-columns=NS:.metadata.namespace,NAME:.metadata.name,IMAGE:.spec.image`; + a blank IMAGE column means that cluster takes the operator default and + will move to mariadb:12.3.3 on its next reconcile. + affectedResources: + - group: k8s.mariadb.com + kinds: + - MariaDB + stepsByDeployer: + - deployers: [helm, helmfile] + steps: + - id: enable-dataplane-autoupdate + description: >- + kubectl patch mariadb mariadb -n slurm --type merge -p + '{"spec":{"updateStrategy":{"autoUpdateDataPlane":true}}}' + reason: >- + Upstream requires this before the operator moves, so the operator + updates the init and agent containers instead of leaving them + behind at the prior version. Repeat for every MariaDB resource + the precondition listed. + - id: upgrade-crds + description: >- + helm upgrade --install mariadb-operator-crds + oci://ghcr.io/mariadb-operator/charts/mariadb-operator-crds + --version 26.10.0 + reason: >- + CRDs go first, and in place. helm uninstall on the CRD chart + deletes the CRDs and cascade-deletes every MariaDB, User, + Database and Grant with them. + - id: upgrade-operator + description: >- + Re-run install.sh (helm) or helmfile apply (helmfile). + reason: >- + Moves the operator to 26.10.0 once the new CRD schema is + Established. + - id: revert-dataplane-autoupdate + description: >- + kubectl patch mariadb mariadb -n slurm --type merge -p + '{"spec":{"updateStrategy":{"autoUpdateDataPlane":false}}}' + reason: >- + Upstream recommends returning it to false so a later operator + bump does not update the data plane unattended. + - steps: + - id: enable-dataplane-autoupdate + description: >- + kubectl patch mariadb mariadb -n slurm --type merge -p + '{"spec":{"updateStrategy":{"autoUpdateDataPlane":true}}}' + reason: >- + Same upstream requirement, applied out of band before the sync so + it lands ahead of the operator. Repeat for every MariaDB resource + the precondition listed. A pruning Argo CD or Flux configuration + will revert this field on the next sync, so run the sync below + promptly after patching. + - id: sync-crds + description: >- + Sync or reconcile the mariadb-operator-crds release to 26.10.0 + before the operator release. + reason: >- + Neither Flux nor Argo CD applies a changed crds/ directory on + upgrade, and the CRD chart must never be pruned or deleted to + achieve the version change: that cascade-deletes every MariaDB. + - id: sync-operator + description: >- + Sync or reconcile the mariadb-operator release. + reason: >- + Moves the operator to 26.10.0 once the new CRD schema is + Established. + - id: revert-dataplane-autoupdate + description: >- + kubectl patch mariadb mariadb -n slurm --type merge -p + '{"spec":{"updateStrategy":{"autoUpdateDataPlane":false}}}' + reason: >- + Upstream recommends returning it to false. If the field is + managed in git, set it there instead so the next sync does not + reintroduce true. + references: + - https://github.com/mariadb-operator/mariadb-operator/blob/main/docs/releases/UPGRADE_26.10.0.md + - https://github.com/mariadb-operator/mariadb-operator/releases/tag/26.10.0 diff --git a/recipes/components/slurm-accounting-mariadb/values.yaml b/recipes/components/slurm-accounting-mariadb/values.yaml index 05dd1c1dab..38ed103b67 100644 --- a/recipes/components/slurm-accounting-mariadb/values.yaml +++ b/recipes/components/slurm-accounting-mariadb/values.yaml @@ -13,6 +13,15 @@ fullnameOverride: mariadb namespaceOverride: slurm mariadb: + # Engine pinned explicitly. mariadb-operator 26.10.0 changed its default + # server image to mariadb:12.3.3; without a pin, a fresh slurm_acct_db + # cluster would silently come up on a new MariaDB major version while + # existing clusters kept 11.8.8, and slurmdbd's supported MariaDB matrix + # has not been checked against 12.3. Pinning also puts the server image + # into the rendered CR, where the BOM can see it: the operator's own + # default lives in its runtime config block and is invisible to a + # render-based BOM. Moving to 12.3 is its own change, with its own UAT. + image: mariadb:11.8.8 rootPasswordSecretKeyRef: name: mariadb-root-password key: root diff --git a/recipes/registry.yaml b/recipes/registry.yaml index 6361fa965e..9502e47f89 100644 --- a/recipes/registry.yaml +++ b/recipes/registry.yaml @@ -1135,7 +1135,7 @@ components: defaultRepository: oci://ghcr.io/mariadb-operator/charts defaultChart: mariadb-operator-crds # renovate: datasource=docker depName=ghcr.io/mariadb-operator/charts/mariadb-operator-crds - defaultVersion: "26.6.0" + defaultVersion: "26.10.0" defaultNamespace: mariadb-system - name: mariadb-operator @@ -1144,11 +1144,13 @@ components: - mariadboperator healthCheck: assertFile: checks/mariadb-operator/health-check.yaml + upgrades: + file: components/mariadb-operator/upgrades.yaml helm: defaultRepository: oci://ghcr.io/mariadb-operator/charts defaultChart: mariadb-operator # renovate: datasource=docker depName=ghcr.io/mariadb-operator/charts/mariadb-operator - defaultVersion: "26.6.0" + defaultVersion: "26.10.0" defaultNamespace: mariadb-system nodeScheduling: system: @@ -1178,7 +1180,7 @@ components: defaultRepository: oci://ghcr.io/mariadb-operator/charts defaultChart: mariadb-cluster # renovate: datasource=docker depName=ghcr.io/mariadb-operator/charts/mariadb-cluster - defaultVersion: "26.6.0" + defaultVersion: "26.10.0" defaultNamespace: slurm storageClassPaths: - mariadb.storage.storageClassName From 13a7b7852197d242565c91da5801801e0e793216 Mon Sep 17 00:00:00 2001 From: Carlos Eduardo Arango Gutierrez Date: Mon, 21 Sep 2026 16:07:14 +0200 Subject: [PATCH 4/9] fix(recipes): gate the MariaDB data-plane revert on update completion The upgrade record moved from "upgrade the operator" straight to "revert autoUpdateDataPlane", with nothing between them. The operator applies the new init and agent images asynchronously, so a resource still mid-roll when the flag flips back is stranded on the old data-plane version against a 26.10.0 operator, which is the exact skew the record exists to prevent. Raised by CodeRabbit on the PR. Both deployer groups gain an await-dataplane-update step before the revert, waiting on Updated=True and then Ready=True. Both condition types were checked against api/v1alpha1/condition_types.go at tag 26.10.0 rather than taken from the suggestion: ConditionTypeUpdated is documented there as indicating that an update completed successfully. The step names resources individually instead of passing --all, and the reason field says why. HasPendingUpdate and IsUpdating both treat a nil Updated condition as false, so the condition is simply absent until an update is triggered, and kubectl wait does not return early on an absent condition. A blanket --all --all-namespaces wait would therefore burn its full timeout on every instance that had no roll to do. Chasing that turned up the larger correction. GetDataPlaneInitContainer and GetDataPlaneAgent both fail unless IsHAEnabled, which is replication or Galera. The init container and agent are the HA data plane and do not exist otherwise, so on AICR's own accounting database (galera disabled, replicas 1) the patch is accepted and does nothing. The record and the catalog notes now say so, and the precondition query gained GALERA and REPLICATION columns, so an operator can see which of their instances the data-plane steps actually apply to instead of running them blind against every row. Signed-off-by: Carlos Eduardo Arango Gutierrez --- docs/user/component-catalog.md | 31 +++++++++- .../components/mariadb-operator/upgrades.yaml | 58 ++++++++++++++++--- 2 files changed, 78 insertions(+), 11 deletions(-) diff --git a/docs/user/component-catalog.md b/docs/user/component-catalog.md index 6554fd9ded..0e822cc6ef 100644 --- a/docs/user/component-catalog.md +++ b/docs/user/component-catalog.md @@ -1563,11 +1563,22 @@ plane has to move with the operator. `updateStrategy.autoUpdateDataPlane` defaults to `false`, so an operator upgraded without setting it first runs `26.10.0` against init and agent containers left at the prior version. +The init container and agent are the HA data plane, so they exist only where +Galera or replication is enabled. AICR's accounting database ships as a single +non-HA instance (`galera.enabled: false`, `replicas: 1`), so steps 1 and 5 +below are inert for it: the field is accepted and does nothing. They matter for +any HA `MariaDB` the same operator manages. List what you have with: + +```bash +kubectl get mariadb -A -o custom-columns=NS:.metadata.namespace,NAME:.metadata.name,IMAGE:.spec.image,GALERA:.spec.galera.enabled,REPLICATION:.spec.replication.enabled +``` + Fresh installs are unaffected. To migrate an existing cluster, set the flag **before** the operator moves, then upgrade CRDs first and the operator second: -1. Enable data-plane auto-update on every MariaDB the operator manages (AICR's - accounting database is `mariadb` in namespace `slurm`): +1. Enable data-plane auto-update on every **HA** MariaDB the operator manages. + AICR's own accounting database is `mariadb` in namespace `slurm` and is not + HA, so this is a no-op for it: ```bash kubectl patch mariadb mariadb -n slurm --type merge \ -p '{"spec":{"updateStrategy":{"autoUpdateDataPlane":true}}}' @@ -1577,7 +1588,21 @@ Fresh installs are unaffected. To migrate an existing cluster, set the flag every `MariaDB`, `User`, `Database` and `Grant` with them. 3. Upgrade `mariadb-operator` to `26.10.0` (re-run `install.sh`, `helmfile apply`, or sync the release). -4. Return the flag to `false` so a later operator bump does not update the data +4. For each HA MariaDB patched in step 1, wait for the roll to finish before + continuing. The operator applies the new init and agent images + asynchronously, and reverting the flag mid-update strands that resource on + the old data-plane version against a `26.10.0` operator: + ```bash + kubectl wait mariadb -n \ + --for=condition=Updated=True --timeout=15m + kubectl wait mariadb -n \ + --for=condition=Ready=True --timeout=15m + ``` + Name each resource rather than passing `--all`. The `Updated` condition is + absent until an update is triggered, and `kubectl wait` does not return + early on an absent condition, so a blanket wait burns the full timeout on + every instance that had no roll to do. +5. Return the flag to `false` so a later operator bump does not update the data plane unattended. If the field is managed in git, set it there. The same release changes the operator's default server image to diff --git a/recipes/components/mariadb-operator/upgrades.yaml b/recipes/components/mariadb-operator/upgrades.yaml index c05e1371fd..682384330c 100644 --- a/recipes/components/mariadb-operator/upgrades.yaml +++ b/recipes/components/mariadb-operator/upgrades.yaml @@ -37,13 +37,18 @@ transitions: mariadb:12.3.3; AICR pins mariadb:11.8.8 in the slurm-accounting-mariadb values, so a cluster bundled from this recipe is unaffected, but any MariaDB CR that omits spec.image will come up on a new MariaDB major - version. + version. The init container and agent are the HA data plane, so they + exist only where Galera or replication is enabled; the data-plane steps + below are inert on a single-instance non-HA MariaDB, which is what the + accounting database AICR ships is by default. precondition: >- Know which MariaDB resources the operator manages and whether any omits spec.image. Check with - `kubectl get mariadb -A -o custom-columns=NS:.metadata.namespace,NAME:.metadata.name,IMAGE:.spec.image`; + `kubectl get mariadb -A -o custom-columns=NS:.metadata.namespace,NAME:.metadata.name,IMAGE:.spec.image,GALERA:.spec.galera.enabled,REPLICATION:.spec.replication.enabled`; a blank IMAGE column means that cluster takes the operator default and - will move to mariadb:12.3.3 on its next reconcile. + will move to mariadb:12.3.3 on its next reconcile. Rows where both + GALERA and REPLICATION are absent or false have no data plane, so only + the CRD and operator upgrades apply to them. affectedResources: - group: k8s.mariadb.com kinds: @@ -58,8 +63,10 @@ transitions: reason: >- Upstream requires this before the operator moves, so the operator updates the init and agent containers instead of leaving them - behind at the prior version. Repeat for every MariaDB resource - the precondition listed. + behind at the prior version. Repeat for every HA MariaDB the + precondition listed. On a non-HA instance the field is accepted + and does nothing, because there is no agent or init container to + update. - id: upgrade-crds description: >- helm upgrade --install mariadb-operator-crds @@ -75,6 +82,23 @@ transitions: reason: >- Moves the operator to 26.10.0 once the new CRD schema is Established. + - id: await-dataplane-update + description: >- + For each HA MariaDB patched in the first step, wait for the roll + to finish before continuing: + `kubectl wait mariadb -n + --for=condition=Updated=True --timeout=15m`, then the same with + `--for=condition=Ready=True`. + reason: >- + The operator applies the new init and agent images + asynchronously, so reverting the flag while a resource is still + updating strands it on the old data-plane version against a + 26.10.0 operator, which is the skew this record exists to + prevent. Name each resource rather than passing --all: the + Updated condition is absent until an update is triggered, and + kubectl wait does not return early on an absent condition, so a + blanket wait burns the full timeout on every instance that had + no roll to do. - id: revert-dataplane-autoupdate description: >- kubectl patch mariadb mariadb -n slurm --type merge -p @@ -89,9 +113,10 @@ transitions: '{"spec":{"updateStrategy":{"autoUpdateDataPlane":true}}}' reason: >- Same upstream requirement, applied out of band before the sync so - it lands ahead of the operator. Repeat for every MariaDB resource - the precondition listed. A pruning Argo CD or Flux configuration - will revert this field on the next sync, so run the sync below + it lands ahead of the operator. Repeat for every HA MariaDB the + precondition listed; on a non-HA instance the field is accepted + and does nothing. A pruning Argo CD or Flux configuration will + revert this field on the next sync, so run the sync below promptly after patching. - id: sync-crds description: >- @@ -107,6 +132,23 @@ transitions: reason: >- Moves the operator to 26.10.0 once the new CRD schema is Established. + - id: await-dataplane-update + description: >- + For each HA MariaDB patched in the first step, wait for the roll + to finish before continuing: + `kubectl wait mariadb -n + --for=condition=Updated=True --timeout=15m`, then the same with + `--for=condition=Ready=True`. + reason: >- + The operator applies the new init and agent images + asynchronously, so reverting the flag while a resource is still + updating strands it on the old data-plane version against a + 26.10.0 operator, which is the skew this record exists to + prevent. Name each resource rather than passing --all: the + Updated condition is absent until an update is triggered, and + kubectl wait does not return early on an absent condition, so a + blanket wait burns the full timeout on every instance that had + no roll to do. - id: revert-dataplane-autoupdate description: >- kubectl patch mariadb mariadb -n slurm --type merge -p From d0fb56ef02c2070d4a91d74edfd878ff52bff545 Mon Sep 17 00:00:00 2001 From: Carlos Eduardo Arango Gutierrez Date: Mon, 21 Sep 2026 20:25:00 +0200 Subject: [PATCH 5/9] fix(recipes): scope the MariaDB CRD upgrade to the release namespace The upgrade record's CRD step ran `helm upgrade --install` with no `--namespace`. Helm scopes a release by namespace, so the request lands in whatever namespace the kubeconfig context happens to point at. If that is not where the release lives, `--install` does not find it and Helm installs a second release, which then fights the first for ownership of the cluster-scoped CRDs. That is a bad outcome for the one chart this record already warns must never be removed, since losing the CRDs cascade-deletes every MariaDB, User, Database and Grant. Raised by CodeRabbit on the PR. The step now confirms the namespace with `helm list -A` before upgrading and passes `--namespace`. It names `mariadb-system` because that is the registry default and no overlay overrides it, verified rather than assumed, while telling the operator to substitute what `helm list` actually reported so an inherited bundle on a different layout is not silently mis-targeted. The catalog notes carry the same command and the same reasoning. Scoped to this one step deliberately. The Argo CD and Flux group syncs the release rather than invoking helm, and the operator step re-runs install.sh or helmfile apply, so neither carries a bare helm invocation that could drift from the release namespace. Signed-off-by: Carlos Eduardo Arango Gutierrez --- docs/user/component-catalog.md | 18 +++++++++++++++--- .../components/mariadb-operator/upgrades.yaml | 16 +++++++++++++--- 2 files changed, 28 insertions(+), 6 deletions(-) diff --git a/docs/user/component-catalog.md b/docs/user/component-catalog.md index 0e822cc6ef..dc7ae7241d 100644 --- a/docs/user/component-catalog.md +++ b/docs/user/component-catalog.md @@ -1583,9 +1583,21 @@ Fresh installs are unaffected. To migrate an existing cluster, set the flag kubectl patch mariadb mariadb -n slurm --type merge \ -p '{"spec":{"updateStrategy":{"autoUpdateDataPlane":true}}}' ``` -2. Upgrade `mariadb-operator-crds` to `26.10.0` **in place**. Never - `helm uninstall` the CRD chart: that deletes the CRDs and cascade-deletes - every `MariaDB`, `User`, `Database` and `Grant` with them. +2. Upgrade `mariadb-operator-crds` to `26.10.0` **in place**. Confirm which + namespace the existing release is in first, because Helm scopes a release + by namespace: without `--namespace` the request lands in whatever namespace + the kubeconfig context points at, `--install` does not find the existing + release, and Helm installs a second one that then fights the first for + ownership of the cluster-scoped CRDs. `mariadb-system` is the registry + default and no overlay overrides it, but an inherited bundle may differ. + ```bash + helm list -A | grep mariadb-operator-crds + helm upgrade --install mariadb-operator-crds \ + oci://ghcr.io/mariadb-operator/charts/mariadb-operator-crds \ + --version 26.10.0 --namespace mariadb-system + ``` + Never `helm uninstall` the CRD chart: that deletes the CRDs and + cascade-deletes every `MariaDB`, `User`, `Database` and `Grant` with them. 3. Upgrade `mariadb-operator` to `26.10.0` (re-run `install.sh`, `helmfile apply`, or sync the release). 4. For each HA MariaDB patched in step 1, wait for the roll to finish before diff --git a/recipes/components/mariadb-operator/upgrades.yaml b/recipes/components/mariadb-operator/upgrades.yaml index 682384330c..ec4acbb5fe 100644 --- a/recipes/components/mariadb-operator/upgrades.yaml +++ b/recipes/components/mariadb-operator/upgrades.yaml @@ -69,13 +69,23 @@ transitions: update. - id: upgrade-crds description: >- - helm upgrade --install mariadb-operator-crds + Confirm the namespace the existing release lives in with + `helm list -A | grep mariadb-operator-crds`, then upgrade in + place: `helm upgrade --install mariadb-operator-crds oci://ghcr.io/mariadb-operator/charts/mariadb-operator-crds - --version 26.10.0 + --version 26.10.0 --namespace mariadb-system`, substituting the + namespace the previous command reported. reason: >- CRDs go first, and in place. helm uninstall on the CRD chart deletes the CRDs and cascade-deletes every MariaDB, User, - Database and Grant with them. + Database and Grant with them. --namespace is not optional here: + Helm scopes a release by namespace, so without it the request + lands in whatever namespace the kubeconfig context points at, + --install does not find the existing release, and Helm installs + a second one that then fights the first for ownership of + cluster-scoped CRDs. mariadb-system is the registry default and + no overlay overrides it, but an inherited bundle may differ, + which is what the helm list confirms. - id: upgrade-operator description: >- Re-run install.sh (helm) or helmfile apply (helmfile). From 0c113a0ae2a6f7c64d3fb059c4073a12768a7e00 Mon Sep 17 00:00:00 2001 From: Carlos Eduardo Arango Gutierrez Date: Mon, 28 Sep 2026 16:22:02 +0200 Subject: [PATCH 6/9] chore(recipes): bump MariaDB charts to 26.10.1 The 2026-09-28 drift report moved mariadb-operator, mariadb-operator-crds and mariadb-cluster past this PR's 26.10.0 pins. The three move together, as before. 26.10.1 is a patch on top of 26.10.0. The CRD delta is additive and optional only: MariaDB gains updateStrategy.mariadbAutoUpgradeEnabled, MaxScale gains filters, services[].filters, volumes and status.filtersSpec, with no removals, no new required field at an existing level and no served or storage version change. Under AICR's values the mariadb-operator render moves only the operator image tag, the version labels and the config checksum that tracks them, and the mariadb-cluster render moves only its chart label. The operator chart's values.yaml is byte-identical to 26.10.0, so config.mariadbImage stays mariadb:12.3.3 and the mariadb:11.8.8 engine pin in slurm-accounting-mariadb neither moves nor needs to. Upgrade record. UPGRADE_26.10.1.md "only applies if you are updating from a version prior to 26.10.x, otherwise you may upgrade directly", and for that older origin it keeps 26.10.0's procedure: set autoUpdateDataPlane before the operator moves, CRDs first, then the operator, then revert. Two changes follow from that. - The existing manual record keeps from "<26.10.0" and widens its to ceiling from 26.10.0 to 26.10.1, with the versions in its steps moved to the pin. Left at 26.10.0, the check tells an operator on 26.6.0, which is the path every earlier AICR release takes, to stop at 26.10.0 first: aicr upgrade-check reported "blocked ... Upgrade to 26.10.0 first" for 26.6.0 -> 26.10.1 with the old ceiling and reports manual with the five steps after. - A new safe record covers from ">=26.10.0 <26.10.1" to 26.10.1. Without it check-upgrade-records fails, because nothing describes an operator on 26.10.0 against a 26.10.1 pin. Its verifiedBy is the upgrade guide's exemption for 26.10.x origins plus the release note. The operator code agrees: the only mariadb container change is MARIADB_AUTO_UPGRADE, set only when the new flag is true, and the flag defaults to false. manual here would block the main path as well: with this record flipped to manual, upgrade-check reports 26.6.0 -> 26.10.1 as blocked for crossing two recorded boundaries. The gate was mutation-checked: dropping verifiedBy, lifting the ceiling past the pin, and emptying the from range each fail with the matching violation. docs/user/component-catalog.md now targets 26.10.1 and says a cluster already on 26.10.0 needs none of the steps. make bom-docs moves the three rows and the operator image to 26.10.1 and nothing else. make update-goldens touches the same seven *-training-slurm leaves as the 26.10.0 bump and no other leaf. Signed-off-by: Carlos Eduardo Arango Gutierrez --- docs/user/component-catalog.md | 28 ++++---- docs/user/container-images.md | 8 +-- .../testdata/catalog_parity_golden.yaml | 14 ++-- .../components/mariadb-operator/upgrades.yaml | 67 +++++++++++++------ recipes/registry.yaml | 6 +- 5 files changed, 78 insertions(+), 45 deletions(-) diff --git a/docs/user/component-catalog.md b/docs/user/component-catalog.md index dc7ae7241d..36df0ee9aa 100644 --- a/docs/user/component-catalog.md +++ b/docs/user/component-catalog.md @@ -1555,13 +1555,14 @@ also installs `computedomains` from its chart. This pairing has not yet been verified on a live OpenShift cluster; see [NVIDIA/aicr#2969](https://github.com/NVIDIA/aicr/issues/2969). -### `mariadb-operator`: `26.6.0` (or earlier) to `26.10.0` +### `mariadb-operator`: `26.6.0` (or earlier) to `26.10.1` `26.10.0` changes the replication configuration rendered by the MariaDB init container and the replication liveness probe served by the agent, so the data -plane has to move with the operator. `updateStrategy.autoUpdateDataPlane` -defaults to `false`, so an operator upgraded without setting it first runs -`26.10.0` against init and agent containers left at the prior version. +plane has to move with the operator, and `26.10.1` keeps that requirement. +`updateStrategy.autoUpdateDataPlane` defaults to `false`, so an operator +upgraded without setting it first runs `26.10.1` against init and agent +containers left at the prior version. The init container and agent are the HA data plane, so they exist only where Galera or replication is enabled. AICR's accounting database ships as a single @@ -1573,8 +1574,11 @@ any HA `MariaDB` the same operator manages. List what you have with: kubectl get mariadb -A -o custom-columns=NS:.metadata.namespace,NAME:.metadata.name,IMAGE:.spec.image,GALERA:.spec.galera.enabled,REPLICATION:.spec.replication.enabled ``` -Fresh installs are unaffected. To migrate an existing cluster, set the flag -**before** the operator moves, then upgrade CRDs first and the operator second: +Fresh installs are unaffected, and so is a cluster already on `26.10.0`: +upstream's `26.10.1` guide applies only when coming from before `26.10.x`, and +`26.10.1` adds only optional CRD fields. To migrate an existing cluster from +`26.6.0` or earlier, set the flag **before** the operator moves, then upgrade +CRDs first and the operator second: 1. Enable data-plane auto-update on every **HA** MariaDB the operator manages. AICR's own accounting database is `mariadb` in namespace `slurm` and is not @@ -1583,7 +1587,7 @@ Fresh installs are unaffected. To migrate an existing cluster, set the flag kubectl patch mariadb mariadb -n slurm --type merge \ -p '{"spec":{"updateStrategy":{"autoUpdateDataPlane":true}}}' ``` -2. Upgrade `mariadb-operator-crds` to `26.10.0` **in place**. Confirm which +2. Upgrade `mariadb-operator-crds` to `26.10.1` **in place**. Confirm which namespace the existing release is in first, because Helm scopes a release by namespace: without `--namespace` the request lands in whatever namespace the kubeconfig context points at, `--install` does not find the existing @@ -1594,16 +1598,16 @@ Fresh installs are unaffected. To migrate an existing cluster, set the flag helm list -A | grep mariadb-operator-crds helm upgrade --install mariadb-operator-crds \ oci://ghcr.io/mariadb-operator/charts/mariadb-operator-crds \ - --version 26.10.0 --namespace mariadb-system + --version 26.10.1 --namespace mariadb-system ``` Never `helm uninstall` the CRD chart: that deletes the CRDs and cascade-deletes every `MariaDB`, `User`, `Database` and `Grant` with them. -3. Upgrade `mariadb-operator` to `26.10.0` (re-run `install.sh`, `helmfile +3. Upgrade `mariadb-operator` to `26.10.1` (re-run `install.sh`, `helmfile apply`, or sync the release). 4. For each HA MariaDB patched in step 1, wait for the roll to finish before continuing. The operator applies the new init and agent images asynchronously, and reverting the flag mid-update strands that resource on - the old data-plane version against a `26.10.0` operator: + the old data-plane version against a `26.10.1` operator: ```bash kubectl wait mariadb -n \ --for=condition=Updated=True --timeout=15m @@ -1617,8 +1621,8 @@ Fresh installs are unaffected. To migrate an existing cluster, set the flag 5. Return the flag to `false` so a later operator bump does not update the data plane unattended. If the field is managed in git, set it there. -The same release changes the operator's default server image to -`mariadb:12.3.3`. AICR pins `mariadb:11.8.8` in +`26.10.0` also changes the operator's default server image to +`mariadb:12.3.3`, and `26.10.1` keeps it. AICR pins `mariadb:11.8.8` in `recipes/components/slurm-accounting-mariadb/values.yaml`, so a cluster bundled from this recipe stays on `11.8.8`; the pin also puts the server image into the rendered `MariaDB` resource, where the BOM records it. Any `MariaDB` that omits diff --git a/docs/user/container-images.md b/docs/user/container-images.md index beaf11453a..9023978f6f 100644 --- a/docs/user/container-images.md +++ b/docs/user/container-images.md @@ -57,8 +57,8 @@ _Rendering fidelity:_ `catalog-parity: charts are rendered with the shared recip | kube-prometheus-stack | helm | prometheus-community/kube-prometheus-stack | 84.4.0 | 8 | | kubeflow-trainer | helm | kubeflow-trainer | 2.2.0 | 4 | | kueue | helm | kueue | 0.19.6 | 1 | -| mariadb-operator | helm | mariadb-operator | 26.10.0 | 1 | -| mariadb-operator-crds | helm | mariadb-operator-crds | 26.10.0 | 0 | +| mariadb-operator | helm | mariadb-operator | 26.10.1 | 1 | +| mariadb-operator-crds | helm | mariadb-operator-crds | 26.10.1 | 0 | | network-operator | helm | nvidia/network-operator | 26.4.1 | 12 | | network-operator-ocp | manifest | — | — | 0 | | network-operator-ocp-olm | manifest | — | — | 0 | @@ -79,7 +79,7 @@ _Rendering fidelity:_ `catalog-parity: charts are rendered with the shared recip | slinky-slurm-operator | helm | slurm-operator | 1.2.2 | 2 | | slinky-slurm-operator-crds | helm | slurm-operator-crds | 1.2.2 | 0 | | slinky-topograph | helm | topograph/topograph | 1.0.0 | 1 | -| slurm-accounting-mariadb | helm | mariadb-cluster | 26.10.0 | 1 | +| slurm-accounting-mariadb | helm | mariadb-cluster | 26.10.1 | 1 | ## Version variants @@ -249,7 +249,7 @@ _No images extracted._ ### mariadb-operator -- `ghcr.io/mariadb-operator/mariadb-operator:26.10.0` +- `ghcr.io/mariadb-operator/mariadb-operator:26.10.1` ### mariadb-operator-crds diff --git a/pkg/recipe/testdata/catalog_parity_golden.yaml b/pkg/recipe/testdata/catalog_parity_golden.yaml index b8795ab6ed..1c4cd53499 100644 --- a/pkg/recipe/testdata/catalog_parity_golden.yaml +++ b/pkg/recipe/testdata/catalog_parity_golden.yaml @@ -17,32 +17,32 @@ eks-ubuntu: bc8d2ac072df16e990ecf76ceb60bfd0be8dc854867d9b2fbd9c5daf05c215f8 gb200-any: f886178cf74ec415ec2e95e9a32f2b8c41416684a62ef5cbe277288c14699c1f gb200-eks-ubuntu-inference-dynamo: 7c205fbad4c98c153b1b2b8784a975959787e19aa3ce616fdccb0bec97ce4b80 gb200-eks-ubuntu-training-kubeflow: b1590df9addcc3ff3386e0a2d25e658396731f67b320573008d3426ead84c2a4 -gb200-eks-ubuntu-training-slurm: 2c9e0ad3004b50ae799026da18a262b95675c7baca96218f15a1bf6fbc2230c5 +gb200-eks-ubuntu-training-slurm: 7e9b4e16b61e2fb527b057b6ffcca8a30528138e06c9e7bfcc6b364076881c4f gb200-gke-cos-inference-dynamo: 20400798cbb2c9e65265a88e9e72a898f8b132fc044b92e0c915f2169e89512a gb200-gke-cos-training-kubeflow: 77064b09640222b09ea169f2c7064797224c2121d2a184c90796651613305112 -gb200-gke-cos-training-slurm: 8dd15a84094e104a8e562da26de003a88493e943b8e5a0d3122e337a1a85d48b +gb200-gke-cos-training-slurm: 413067bfaba04f77a53f65b9fe892e0942ce3977f49ab236bbe2035f6a683ff9 gb200-oke-ubuntu-inference-dynamo: 4166375b2e48875a7ee2a4bf7c6b45762367d3d5ee2a4d326a97c44533a76ffa gb200-oke-ubuntu-training-kubeflow: ff62cde41872e5fb9c52c97d2094a7952e5d514970a753e91b815fa66f0c90a6 gb300-any: 96aa04360e1f10f8b42e5bd1f918d558d41339cb002bf515ef6dac53f3c9bd5f gb300-eks-ubuntu-inference-dynamo: 2b3d513ba6f063648b7bcf3e38ac3e9c236be8328f8cdbb5599cc668c3ab66a0 gb300-eks-ubuntu-training-kubeflow: 8874fdf7b8060fca11f7412e2c7090d0869c068ad5d352be7b4c7957f52ab311 -gb300-eks-ubuntu-training-slurm: 70f1bfa28fbbeaa0711d54dbd7c0a265bc5fab392c4ad10cd51528711c0a40d1 +gb300-eks-ubuntu-training-slurm: 3b2001ec27233f382d518ebc2fc091186b74eea8cecc5d6898d045b9d0dd158e gb300-generic-ubuntu-training: 8cd1c26e2d7b9d7f0605695fbb32d98f5204e282b7b0e52473f40b9761287bdf h100-aks-ubuntu-inference-dynamo: 54ad5bcf3ecf22ade1720091d8ab3a260ecb7b0784824417c1d77683693e6d5f h100-aks-ubuntu-training-kubeflow: 9936cf1a5dce954f41c2076ba1bcaa1e029e19bee4d0660e07fc39e08b682a15 -h100-aks-ubuntu-training-slurm: 50add28d1ad55791fccfc681901cf4cad9e7d6f0d3885f23258c6b42df47f698 +h100-aks-ubuntu-training-slurm: d25674a9b57cd110da31466c16311f22147a6ce3dbdeb61531add084915d5949 h100-any: 902ee0497cc4358441c42f533f01438be066b318def504eaf30859fd8f9b90d2 h100-bcm-ubuntu-training-kubeflow: 7e850295309d0dfb6a65b990a52b69fd3a892a352b846a909e956b41e2485c18 h100-eks-ubuntu-inference-dynamo: b5c1edc0859c57fcbbf8a429312f1ccc225793c28774405b6692550aaa81b50e h100-eks-ubuntu-inference-nim: eed32e85aa44bd0734aefaf7214866db7a80d28711d65bb423d47ea4c1113862 h100-eks-ubuntu-training-kubeflow: 03990c0bf9544f1914f55fdb57a53b4dd2214fa922244994b8cfce538f3d143a -h100-eks-ubuntu-training-slurm: cf3a6623ffbe0f7feee9a4a22627ef28bf8eb3ad9061a0d02c2f0f28fa2725f2 +h100-eks-ubuntu-training-slurm: e528a54de4b0f9a37406bbe3aa4725ad0fd38a6d2b55ac65b3bf4eebaf0e13d2 h100-gke-cos-inference-dynamo: 3392baf8b9bcec9eb7d3cfe5d316dd9d32b1f4277e700c29c1b67c65efb8eb9d h100-gke-cos-training-kubeflow: 16c3fe5d2f954caadba58a3d319acfd2db229ed4f0474d78ac30157483e2c5e0 -h100-gke-cos-training-slurm: 5f4598d921663870b38837455252a7ae097888a05fff77be85d462a356ccd17e +h100-gke-cos-training-slurm: cf1f6d42132eb1bba7f28a4bef4304328e9bfd2593e7bd2dd78b98c0c83b21ff h100-kind-inference-dynamo: 5552082356c8339d3c54ee6e275659e690913c138448dd1f5e1eb4a6e9703a5d h100-kind-training-kubeflow: 52bc7adcf5b36ec774eb1d5212f63eea9a4253130ce6d1b6d80199d123115d01 -h100-kind-training-slurm: 44f962318e08558aef36a886abf25d659a3ba46b2d8fcb1e756cb6c87e38fef6 +h100-kind-training-slurm: 7a6acbf833aee54895ec9ea29c18faa90ac9f401f100800a333eb154f8e38319 h200-any: c560a926b1997210654edee1d2d299f59ca7bd58d7ae11679b4649ea63b095dd h200-eks-inference: e8108add208b99f58fb9c9f49da13a9a149509075ec730db580b52201e67b1a1 h200-eks-training-kubeflow: 4beaaf1f420c840b42d50b29595013f0cf8674ff4963ff75f9cdbe96805cd66c diff --git a/recipes/components/mariadb-operator/upgrades.yaml b/recipes/components/mariadb-operator/upgrades.yaml index ec4acbb5fe..6cc4ee5c9f 100644 --- a/recipes/components/mariadb-operator/upgrades.yaml +++ b/recipes/components/mariadb-operator/upgrades.yaml @@ -16,28 +16,33 @@ apiVersion: aicr.run/v1beta1 kind: ComponentUpgrades component: mariadb-operator transitions: - # from opens below the pin rather than at 26.6.0: upstream uses CalVer and - # the only 26.x releases are 26.3.0, 26.6.0 and 26.10.0, so an operator - # arriving from any of them crosses the same boundary. Naming 26.6.0 as the - # floor would leave every earlier pin matching nothing. + # from opens below 26.10.0 rather than at 26.6.0: upstream uses CalVer and + # the only 26.x releases below 26.10.0 are 26.3.0 and 26.6.0, so an operator + # arriving from either crosses the same boundary. Naming 26.6.0 as the floor + # would leave every earlier pin matching nothing. + # + # to reaches 26.10.1 because upstream's 26.10.1 guide takes an operator + # from before 26.10.x straight to 26.10.1 with this same procedure; a + # ceiling at 26.10.0 would block that jump at 26.10.0. # # verdict is manual, not safe, and carries no verifiedBy: no UAT lane or # KWOK run has exercised this transition. The procedure below is transcribed # from upstream's own upgrade guide, not vouched for by a run here. - from: "<26.10.0" - to: "26.10.0" + to: ">=26.10.0 <=26.10.1" verdict: manual summary: >- 26.10.0 changes the replication configuration rendered by the MariaDB init container and the replication liveness probe served by the agent, - so the data plane must move with the operator. autoUpdateDataPlane - defaults to false, so an operator upgraded without setting it first runs - 26.10.0 against init and agent containers left at the prior version. - The release also changes the operator's default server image to - mariadb:12.3.3; AICR pins mariadb:11.8.8 in the slurm-accounting-mariadb - values, so a cluster bundled from this recipe is unaffected, but any - MariaDB CR that omits spec.image will come up on a new MariaDB major - version. The init container and agent are the HA data plane, so they + so the data plane must move with the operator, and 26.10.1 keeps that + requirement. autoUpdateDataPlane defaults to false, so an operator + upgraded without setting it first runs 26.10.1 against init and agent + containers left at the prior version. 26.10.0 also changes the + operator's default server image to mariadb:12.3.3; AICR pins + mariadb:11.8.8 in the slurm-accounting-mariadb values, so a cluster + bundled from this recipe is unaffected, but any MariaDB CR that omits + spec.image will come up on a new MariaDB major version. The init + container and agent are the HA data plane, so they exist only where Galera or replication is enabled; the data-plane steps below are inert on a single-instance non-HA MariaDB, which is what the accounting database AICR ships is by default. @@ -73,7 +78,7 @@ transitions: `helm list -A | grep mariadb-operator-crds`, then upgrade in place: `helm upgrade --install mariadb-operator-crds oci://ghcr.io/mariadb-operator/charts/mariadb-operator-crds - --version 26.10.0 --namespace mariadb-system`, substituting the + --version 26.10.1 --namespace mariadb-system`, substituting the namespace the previous command reported. reason: >- CRDs go first, and in place. helm uninstall on the CRD chart @@ -90,7 +95,7 @@ transitions: description: >- Re-run install.sh (helm) or helmfile apply (helmfile). reason: >- - Moves the operator to 26.10.0 once the new CRD schema is + Moves the operator to 26.10.1 once the new CRD schema is Established. - id: await-dataplane-update description: >- @@ -103,7 +108,7 @@ transitions: The operator applies the new init and agent images asynchronously, so reverting the flag while a resource is still updating strands it on the old data-plane version against a - 26.10.0 operator, which is the skew this record exists to + 26.10.1 operator, which is the skew this record exists to prevent. Name each resource rather than passing --all: the Updated condition is absent until an update is triggered, and kubectl wait does not return early on an absent condition, so a @@ -130,7 +135,7 @@ transitions: promptly after patching. - id: sync-crds description: >- - Sync or reconcile the mariadb-operator-crds release to 26.10.0 + Sync or reconcile the mariadb-operator-crds release to 26.10.1 before the operator release. reason: >- Neither Flux nor Argo CD applies a changed crds/ directory on @@ -140,7 +145,7 @@ transitions: description: >- Sync or reconcile the mariadb-operator release. reason: >- - Moves the operator to 26.10.0 once the new CRD schema is + Moves the operator to 26.10.1 once the new CRD schema is Established. - id: await-dataplane-update description: >- @@ -153,7 +158,7 @@ transitions: The operator applies the new init and agent images asynchronously, so reverting the flag while a resource is still updating strands it on the old data-plane version against a - 26.10.0 operator, which is the skew this record exists to + 26.10.1 operator, which is the skew this record exists to prevent. Name each resource rather than passing --all: the Updated condition is absent until an update is triggered, and kubectl wait does not return early on an absent condition, so a @@ -170,3 +175,27 @@ transitions: references: - https://github.com/mariadb-operator/mariadb-operator/blob/main/docs/releases/UPGRADE_26.10.0.md - https://github.com/mariadb-operator/mariadb-operator/releases/tag/26.10.0 + - https://github.com/mariadb-operator/mariadb-operator/blob/main/docs/releases/UPGRADE_26.10.1.md + - https://github.com/mariadb-operator/mariadb-operator/releases/tag/26.10.1 + + # from starts at 26.10.0: an operator below it crosses the 26.10.0 + # boundary, which the record above describes through 26.10.1. + - from: ">=26.10.0 <26.10.1" + to: "26.10.1" + verdict: safe + verifiedBy: >- + Upstream upgrade guide UPGRADE_26.10.1.md (mariadb-operator), which + applies only when updating from a version prior to 26.10.x and + otherwise allows upgrading directly, and the 26.10.1 release note, + which describes it as a patch release on top of 26.10.0. The CRD delta + adds optional fields only. Under AICR's values the mariadb-operator + render moves only the operator image tag, the version labels and the + config checksum that tracks them, and the mariadb-cluster render moves + only its chart label. + summary: >- + Patch release within 26.10.x that adds only optional CRD fields: MariaDB + updateStrategy.mariadbAutoUpgradeEnabled, false by default, and MaxScale + filters and volumes. Nothing to change on upgrade. + references: + - https://github.com/mariadb-operator/mariadb-operator/blob/main/docs/releases/UPGRADE_26.10.1.md + - https://github.com/mariadb-operator/mariadb-operator/releases/tag/26.10.1 diff --git a/recipes/registry.yaml b/recipes/registry.yaml index 9502e47f89..d04b372ee8 100644 --- a/recipes/registry.yaml +++ b/recipes/registry.yaml @@ -1135,7 +1135,7 @@ components: defaultRepository: oci://ghcr.io/mariadb-operator/charts defaultChart: mariadb-operator-crds # renovate: datasource=docker depName=ghcr.io/mariadb-operator/charts/mariadb-operator-crds - defaultVersion: "26.10.0" + defaultVersion: "26.10.1" defaultNamespace: mariadb-system - name: mariadb-operator @@ -1150,7 +1150,7 @@ components: defaultRepository: oci://ghcr.io/mariadb-operator/charts defaultChart: mariadb-operator # renovate: datasource=docker depName=ghcr.io/mariadb-operator/charts/mariadb-operator - defaultVersion: "26.10.0" + defaultVersion: "26.10.1" defaultNamespace: mariadb-system nodeScheduling: system: @@ -1180,7 +1180,7 @@ components: defaultRepository: oci://ghcr.io/mariadb-operator/charts defaultChart: mariadb-cluster # renovate: datasource=docker depName=ghcr.io/mariadb-operator/charts/mariadb-cluster - defaultVersion: "26.10.0" + defaultVersion: "26.10.1" defaultNamespace: slurm storageClassPaths: - mariadb.storage.storageClassName From 2b2a3d70406d32f45f426362ab27cd8336cde09e Mon Sep 17 00:00:00 2001 From: Carlos Eduardo Arango Gutierrez Date: Tue, 22 Sep 2026 12:30:14 +0200 Subject: [PATCH 7/9] chore(recipes): bump kai-scheduler to v0.17.2 The 2026-09-21 drift report names v0.20.1 as the target for this component. That is a false positive and taking it would have been a regression. v0.20.1 is a stale tag whose commit is dated 2025-11-30, ten months older than v0.17.2 (2026-09-16). It has no GitHub Release, ships 159 lines of values against v0.17.2's 347, and still points global.registry at the pre-rename ghcr.io/nvidia/kai-scheduler path. The repository moved to kai-scheduler/KAI-Scheduler and there are no v0.18 or v0.19 tags at all, so the drift tool's semver-max comparison selected a numerically higher tag from an abandoned line. v0.17.2 is the actual latest release, not a prerelease, and is the series the partner question in Slack was about. Everything AICR consumes survives the bump, verified against both charts rather than assumed: global.tolerations, global.nodeSelector (the two paths the registry injects into), postCleanup.enabled, and the three defaultQueue keys. The CRD set is unchanged, six CRDs at identical versions, all served and stored, so queues.scheduling.run.ai/v2 and schedulingshards.kai.scheduler/v1 still back the self-referencing CRs this component's hasSelfRefCRDs flag exists for. The rendered image set stays at twelve from the same two registry paths, so no registry-inventory allowlist entry is needed. Three values keys were removed upstream in v0.17.0: global.fips, renamed to global.fipsMode in v0.17.1, and queuecontroller.certSecretName and admission.certSecretName, which upstream describes as unused because the operator creates and manages the webhook TLS secrets itself. AICR sets none of the three. The secrets the operator now manages carry different names than the chart previously defaulted to; the health check asserts on the kai-operator Deployment and pod phases rather than on secret names, so it is unaffected. The openshift value added in v0.17.0 does not apply here. It exists because the chart's OpenShift auto-detection uses a cluster lookup that cannot work under offline rendering, but recipes/overlays/ocp.yaml sets kai-scheduler to enabled: false, so AICR does not deploy this component on OpenShift at all. An offline render with the value unset produces zero SecurityContextConstraints, matching v0.16.9. Golden parity fixtures regenerated with AICR_UPDATE_GOLDEN=1. The catalog diff touches 57 leaves because kai-scheduler is declared in recipes/overlays/base.yaml rather than per-leaf, so every recipe inheriting base moves with the pin. Signed-off-by: Carlos Eduardo Arango Gutierrez --- docs/user/container-images.md | 26 +- pkg/bundler/testdata/stock_render_golden.yaml | 570 +++++++++--------- .../testdata/catalog_parity_golden.yaml | 118 ++-- recipes/registry.yaml | 2 +- 4 files changed, 358 insertions(+), 358 deletions(-) diff --git a/docs/user/container-images.md b/docs/user/container-images.md index 9023978f6f..d47d737909 100644 --- a/docs/user/container-images.md +++ b/docs/user/container-images.md @@ -53,7 +53,7 @@ _Rendering fidelity:_ `catalog-parity: charts are rendered with the shared recip | k8s-ephemeral-storage-metrics | helm | k8s-ephemeral-storage-metrics/k8s-ephemeral-storage-metrics | 1.19.2 | 1 | | k8s-nim-operator | helm | k8s-nim-operator | 3.1.0 | 1 | | k8s-nim-operator-ocp | helm | k8s-nim-operator | 3.1.0 | 1 | -| kai-scheduler | helm | kai-scheduler | v0.16.9 | 12 | +| kai-scheduler | helm | kai-scheduler | v0.17.2 | 12 | | kube-prometheus-stack | helm | prometheus-community/kube-prometheus-stack | 84.4.0 | 8 | | kubeflow-trainer | helm | kubeflow-trainer | 2.2.0 | 4 | | kueue | helm | kueue | 0.19.6 | 1 | @@ -212,18 +212,18 @@ _No images extracted._ ### kai-scheduler -- `ghcr.io/kai-scheduler/kai-scheduler/admission:v0.16.9` -- `ghcr.io/kai-scheduler/kai-scheduler/binder:v0.16.9` -- `ghcr.io/kai-scheduler/kai-scheduler/crd-upgrader:v0.16.9` -- `ghcr.io/kai-scheduler/kai-scheduler/nodescaleadjuster:v0.16.9` -- `ghcr.io/kai-scheduler/kai-scheduler/numa-placement-exporter:v0.16.9` -- `ghcr.io/kai-scheduler/kai-scheduler/operator:v0.16.9` -- `ghcr.io/kai-scheduler/kai-scheduler/podgroupcontroller:v0.16.9` -- `ghcr.io/kai-scheduler/kai-scheduler/podgrouper:v0.16.9` -- `ghcr.io/kai-scheduler/kai-scheduler/queuecontroller:v0.16.9` -- `ghcr.io/kai-scheduler/kai-scheduler/resourcereservation:v0.16.9` -- `ghcr.io/kai-scheduler/kai-scheduler/scalingpod:v0.16.9` -- `ghcr.io/kai-scheduler/kai-scheduler/scheduler:v0.16.9` +- `ghcr.io/kai-scheduler/kai-scheduler/admission:v0.17.2` +- `ghcr.io/kai-scheduler/kai-scheduler/binder:v0.17.2` +- `ghcr.io/kai-scheduler/kai-scheduler/crd-upgrader:v0.17.2` +- `ghcr.io/kai-scheduler/kai-scheduler/nodescaleadjuster:v0.17.2` +- `ghcr.io/kai-scheduler/kai-scheduler/numa-placement-exporter:v0.17.2` +- `ghcr.io/kai-scheduler/kai-scheduler/operator:v0.17.2` +- `ghcr.io/kai-scheduler/kai-scheduler/podgroupcontroller:v0.17.2` +- `ghcr.io/kai-scheduler/kai-scheduler/podgrouper:v0.17.2` +- `ghcr.io/kai-scheduler/kai-scheduler/queuecontroller:v0.17.2` +- `ghcr.io/kai-scheduler/kai-scheduler/resourcereservation:v0.17.2` +- `ghcr.io/kai-scheduler/kai-scheduler/scalingpod:v0.17.2` +- `ghcr.io/kai-scheduler/kai-scheduler/scheduler:v0.17.2` ### kube-prometheus-stack diff --git a/pkg/bundler/testdata/stock_render_golden.yaml b/pkg/bundler/testdata/stock_render_golden.yaml index 437d369155..be8bf44588 100644 --- a/pkg/bundler/testdata/stock_render_golden.yaml +++ b/pkg/bundler/testdata/stock_render_golden.yaml @@ -57,7 +57,7 @@ a100-aks-ubuntu-training-kubeflow: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -81,12 +81,12 @@ a100-aks-ubuntu-training-kubeflow: 017-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 017-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 017-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: c59cdceff0e9959d375d3c4e6725eb4df735e8979ccefb79f9bd6d75a60935b5 + README.md: 454247f23dc00482aa1e72c5e8747caa65d46d9d1c1a2ae8841c7fd2dab40e13 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: b8757b034c4af4ea4260caf4c3311f2b805a435155323196e8fa30394aff7e1c - checksums.txt: 8f99b2583e2dcf38e6b997da8a5e39d7d3cf86bf410511e2cf58bb76d78f0e02 + bundle-info.yaml: ff17e97e21d0c74fea0c7fbc2f2dff32373e22f55382bd3a20fe54f2fbd6d7f6 + checksums.txt: 6f67e820c1485b16d542aabf62ba887430751b80e4fe68e6ae133f04ae9cad50 deploy.sh: 578de8756d8c7fd3f4cb092af39adaeefd0e3df50e5d248893b42bd1029f4532 - recipe.yaml: 31de158c477835adc03f540590bfa4e53e366df642faad27e257830a2701ea92 + recipe.yaml: 71ddaeb0fb084e544adf2537a50fb9d36e7244213b85cd0e9bc24274e5297ab4 a100-any: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -118,7 +118,7 @@ a100-any: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -133,12 +133,12 @@ a100-any: 011-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 011-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 011-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 9ca6e45a84a07008ffa7cdfa3c51bcaf13a3e992b8069cf6327882d32d8ce806 + README.md: 0a20684beefa34accb90d5c24f0b84e0c1cca4a0ad7c19dfd543fcacd197aa0a UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: ad4f9557a3b9797a2ffb23f6873c1935e283599143f741c823d83798a200132c - checksums.txt: 467ea1ae826459ae2b5e392009d9da59d4e7379587476f76c00b8faa6b932d6a + bundle-info.yaml: 0247ef873e5a3855c91c7bcb1a90afb8f0c970175f71cb57bf731b5aa38c4175 + checksums.txt: 480d21053c4c79a93f9580b40ded9220735bb9fa513762ccfdb954cdb5cca9c8 deploy.sh: ea70804cf5d8c0bb716ccd59ea4a31a1037672453aa11e2e2bfbd20daf55d901 - recipe.yaml: 67ce39f490a229ef7eaf80e15316edd3f19dd077f23b39c12f63a9bb13f0970d + recipe.yaml: 79f2a4b88ebf317916d00684333044439c970e3c470f4bd3f6a3baec97e1fe66 a100-eks-ubuntu-training-kubeflow: 001-aws-ebs-csi-driver/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-aws-ebs-csi-driver/install.sh: 4b3958a35a18427b6ccbefa30abdad829b99178677311ac444eff3e34c6479c6 @@ -183,7 +183,7 @@ a100-eks-ubuntu-training-kubeflow: 010-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 011-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 011-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 011-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 011-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 012-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -207,12 +207,12 @@ a100-eks-ubuntu-training-kubeflow: 016-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 016-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 016-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: c2fb67edc7eca8b6988382312a0aefef868066029c2a3cb7e1e8e59cc6566373 + README.md: ac51f0f1ae803f2268dd729d380734bd7f0c161adc001bc086a712e66e64d5b5 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 7d9b1fdd481ae80b6fe9aa8079bbb3604ec1ce9c11002c985f186f91c5659f01 - checksums.txt: 21aa52ca92161d183c6eb6d4d7dd08894aa73299e4d9ec46c1a564c308f4d8bb + bundle-info.yaml: 737ec4bfde6a0b9a2a12173ea12751515728a35e7bd1ede9f65e3e2ce6cfcb0d + checksums.txt: 0293b44c8892701cfac81213f9ae4fc914b9df647b6eca6433eaae2ef624b188 deploy.sh: 5b2acd33c456f23e8d1f4d574f94b9ba2bce52147876f165a54e3395e55de09b - recipe.yaml: 9c868eb55b01a98513d2e341d7242e9d0b9b1b5969206c6415d4cecdc2abfa30 + recipe.yaml: ce433a1203a76d72711b418bd62c4246fc1c85ccd5db0cf378ec59fcb3ff236e a100-gke-cos-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -258,7 +258,7 @@ a100-gke-cos-training-kubeflow: 010-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 011-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 011-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 011-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 011-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 012-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -282,12 +282,12 @@ a100-gke-cos-training-kubeflow: 016-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 016-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 016-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: e21a4b1766a05e41473e85415eddc8c3c72fac6d5eb3851c5da02c946cb2dfed + README.md: 1b666b5fe758af73910abb4d63d3f6c48ef0370c8a9cca186db1d5588329fb96 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: e9231504d14acfc247811326fdf17edb8022c38a238c3113ceb4792fffb79ea3 - checksums.txt: f565ee5440332343e50bed71c77ab2b534401260273563b2eacfa13a2a143312 + bundle-info.yaml: 2be6e0ecef5201426ddb9746cbdc9422494c73e355688cb73ef3c380884371f3 + checksums.txt: 93413515648eb862b2fb2de83a5743e2eb55977dcb07ccfc69b2462b0b7eef84 deploy.sh: 2b0cd173c38bb27ee4cdb7d6c4d1d94d523b56fed94d6889cacd342b0b5a0dfd - recipe.yaml: 9ba7f55ca95b2b646138e1364ed8cce1ef085c141b6092e9acec1b2e3496a427 + recipe.yaml: 070d6d903ae2cf348f5024c8f994f59e7c3197443db683adfabb9d2336cbfc19 a100-oke-ubuntu-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -319,7 +319,7 @@ a100-oke-ubuntu-training-kubeflow: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -343,12 +343,12 @@ a100-oke-ubuntu-training-kubeflow: 013-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 013-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 013-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: bb7d5d0404f2dc415d3559a7d1e8f1b2288fd6684a76b4758278020a65736424 + README.md: 0a9ba55a75ff6e776b902353c4194cc5742b1037a13e083fd4b3a9b05e2e59a7 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 4e734937ad34f76384eaaa848b203ae607df88334ea31ddbe8e489b0c3f52fbe - checksums.txt: a3f4866685d7443a8519e2245e2b7ea3bf693732d0b51eaea77a673d75860684 + bundle-info.yaml: c9ca3c613a56046fc8e82083c50db368e24e6d3ec06cdbd8f969993b8941505a + checksums.txt: d7df69103aeb48526e5153e9b92b59e9b906cb5dd0d2bdc3d35a5b9a9e1ee248 deploy.sh: 8ebf4bd801a6d8fd6cba8979dc354e9aeeb8d5cfccbee9e6e7262417b175c6f4 - recipe.yaml: 36381c1944cba39d385c0ab8faf89e15bb5cf8c320e384196b56b68e5854d516 + recipe.yaml: 919a0fbefac64e19825288d47645d4a50f51f5e8b4a463de58e6941f1bc4346c aks-ubuntu: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -396,7 +396,7 @@ aks-ubuntu: 010-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 011-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 011-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 011-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 011-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 012-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -411,12 +411,12 @@ aks-ubuntu: 014-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 014-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 014-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 47818d601139c841e2b931899d4b1579acbcf5bcfc6bb6bb064c4f83a0ffeb90 + README.md: 83e666d84365199ce45e80996a44e24db297c027920943415d1eda85741e0d5b UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 052dbe04fd5e7a135bc6e6df50aa560516183938c65b3f3dac132cb143fe0c6f - checksums.txt: 10c3564d5c3e5d3fa518ea444e506669ab8f9b377cd8edd0b58b61f100a5a326 + bundle-info.yaml: 3fe9e8c8daf63e0e1fcf825d8f6f1a0fcc22c6d452da839937c6050a6aa5a129 + checksums.txt: 80e24d8eef645b243547a6d8c1170d8151a00190ef4235a071b58967d8ccd8bf deploy.sh: 1d5c9d627548eabf502d0ca6ecacddce17627e87ebdbd095333df77e8cdad2df - recipe.yaml: 1c4ba900739f229c70ecacaf72ff790e7a554880b226655c32f0284c4076eee7 + recipe.yaml: 697b3f8378c30cbff980b7117f2cfd6667d3a381d5cb94b8ec30db30598c763b b200-any: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -448,7 +448,7 @@ b200-any: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -463,12 +463,12 @@ b200-any: 011-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 011-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 011-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: cf4d7e0922c8821fcac68e37444beff835581194b11b0a11c2ddae7be474c80b + README.md: 215b6e5b0531b685b64d8b69459cc2b7e990eb5e5592e6254706e1cfdbacea87 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 678737aa5616f511a57776d0d357073c70ca2bfeb83d29dbd317ef82964aa039 - checksums.txt: 02e447100626305aa65ee3ee6c3502966dfaced063ae8b3c5ecf9b225227af5b + bundle-info.yaml: 10250603d33b8a156396b874451174970b6e2da4d401fc32ee04497ee231363d + checksums.txt: b4ffe11a8409c55af3a8b22a0f67cd4be9abcbaef0f4cb82fa8f4a47174508dd deploy.sh: ea70804cf5d8c0bb716ccd59ea4a31a1037672453aa11e2e2bfbd20daf55d901 - recipe.yaml: fec141debfbc24173ddcc5e05f3678d11fc936f6092f6f4d24dab9893218fd6a + recipe.yaml: 3921dc2b9fcf1a6ba80d90e4cde2da1ec07cbab410a9c6600a78fd848b875df8 b200-gke-cos-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -537,7 +537,7 @@ b200-gke-cos-inference-dynamo: 015-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 016-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 016-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 016-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 016-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 017-dynamo-platform/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-dynamo-platform/install.sh: 26f4a6ece285df70c933829cf3fc476fd3b61b711f858d86dd77f5abb22bee24 @@ -556,12 +556,12 @@ b200-gke-cos-inference-dynamo: 020-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 020-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 020-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 5703af26dd5ce9982bd5949da24bef64cd5da4ffe5f2f73d3978e52a48c3ae25 + README.md: 6bbf8005ac14beb276f0d640fe85006b4ea3ef364c182d73ca53a87427b1ebfb UPGRADING.md: d27ec18c5dbe463bc50dfdde771821d0a717e350be36a89f87297ada543ba81c - bundle-info.yaml: 4a472490a261894fc68b4a5b67f482ed3fea56d64abe501043f3c342b2c3fb2a - checksums.txt: ed5a971694464d9108a69611b1005affe45648b91a73443894312d10ae6600fd + bundle-info.yaml: a4538237cf0b078c17bace7d4b0b63fe3997102e45c165d0a3a21d7104b16235 + checksums.txt: d627f188b37344261b2ba4075d57a2869f3eb5bd005e016d171475b82f546de8 deploy.sh: 62b3ab91044223177c74d3aee7241f4aeae64e6bdb31481f7da642dbf4556e9a - recipe.yaml: e9db226befc5008771e8e32c6ea5fd998501fd003e502005fbaf322e13fd196a + recipe.yaml: 1efa25592b6f53b79d67ab384bb5cb59fe246d491db47f8295f19119c164da1b b200-gke-cos-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -607,7 +607,7 @@ b200-gke-cos-training-kubeflow: 010-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 011-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 011-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 011-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 011-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 012-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -631,12 +631,12 @@ b200-gke-cos-training-kubeflow: 016-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 016-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 016-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 35ee900dad87a1d7a0ea53ca7f9422f602fbcdfff8884086977f599620f7a686 + README.md: 3488b4068e4d377b17dd38cf059bf0c548ad1b241c1c6eaeb1011ff4ad752c9a UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 910e640f7e7442cb6e8537a11d86b7307096564795f52461a21341f2a175415f - checksums.txt: b061ce0b6c797ec2d3b140b32b32778ccb27c0464e9783d9064809c4b125c283 + bundle-info.yaml: 95155a59f45de69e27aa2deaba077c065ac499202abd99b52a8154905fcf7189 + checksums.txt: 2c58c75401fc5ae334868de391524696dcf47c6d07098d0e918bc3d8fa3e4f5b deploy.sh: 2b0cd173c38bb27ee4cdb7d6c4d1d94d523b56fed94d6889cacd342b0b5a0dfd - recipe.yaml: fbffcad95923a554f5c6ca4d9833cdec38be012ca146a8b1c265487ca531a915 + recipe.yaml: 119732e59306afe2ea3df3fa2be793a4d19cd745e58f29bca9b2094b8b02e087 bcm-inference: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -692,7 +692,7 @@ bcm-inference: 012-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 013-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 013-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 013-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 013-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 014-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 014-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -707,12 +707,12 @@ bcm-inference: 016-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 016-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 016-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 8cf61b75e92017ac8ad83f09b58b101e0506883369e7b31155bc4c4b61492dff + README.md: 29664087c4c34273ea9fcf3e1aa2180dbec477859fe61c5a59e2787c56774c50 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 62faebc11da34bc66e56ba5e8a6d493ee7300c1b4a49ea60685281d3496d2781 - checksums.txt: 2e783d80116d6eecada96939f62a220361697b37875ad4ec13b85b10406c8c91 + bundle-info.yaml: 258dc9a27045190d91e0c782691d6794a61e658a5b51f6ed32b016f31542f3fe + checksums.txt: cd55f49fa0d2187c48366f89c14effa6ad74368cb58f4ad3ef1567a49c9f5a95 deploy.sh: 0e40b3c44ac83591b443c18609eb82ddbdb3f5d410cb8eaff31a5533f9348d6e - recipe.yaml: 8953e615d4d84bd0a860b1e8aea84c00fa1edbf64028c3c1d7db37807357dfa7 + recipe.yaml: 6ac7f074faf7dabb5c2de3c7d0cf876ed0a4b95e09700b9b970864c498dd8f3c eks-ubuntu: 001-aws-ebs-csi-driver/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-aws-ebs-csi-driver/install.sh: 4b3958a35a18427b6ccbefa30abdad829b99178677311ac444eff3e34c6479c6 @@ -752,7 +752,7 @@ eks-ubuntu: 009-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 010-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 010-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 010-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 010-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 010-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 011-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -767,12 +767,12 @@ eks-ubuntu: 013-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 013-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 013-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: f73fdb0f62f176b0cc9b735d3ded5bfeca4539daa2c9e97167b3da7055d573d5 + README.md: 7077931ab6d64a59c5100013a15ea31b567bc1ae6484b55121ba332772df100e UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 866da806c394a3ed15397e03afc376e6be7012328971ce88ce84039ff478d58a - checksums.txt: ab0b7daaa49c1cfcee81c3b107e08aaadc2758eefeb578aef0f80d45a3f96566 + bundle-info.yaml: 0265d6d562ecee620e27f020ae06a0563c296880b53507afe4a36c5eec9b98ca + checksums.txt: 46af000cca2e7b2e2b0819fc6f68b0cdd0f6735892fb162f8c3ffe6f063ec470 deploy.sh: 2fd097b74541a045e1a07751042298f7d295f8071c60bbd9be76029f9ac34959 - recipe.yaml: afeb379a07ad5bcf87007bb99a0aab395959e4a61ef92ed5b46092730f5cdd6e + recipe.yaml: 15356ed0614564b99397ef4caad1265cbeec70dde6abe80ee9fa19d37b169969 gb200-any: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -804,7 +804,7 @@ gb200-any: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -819,12 +819,12 @@ gb200-any: 011-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 011-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 011-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 7b43d55c87cb3312c54d1a52f083ccec7e9f9182ae49aeb2790159acd927eda3 + README.md: 99bc6a57b5a134afababc9641d648ce361b42c11c9b370bb2226996b21fe6127 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 42c13acd0638fc09d941d4cafd2b4e9c4a99f618e1ebf427aaf3956b686a722a - checksums.txt: 7264b1623b4a9482ba592c63ce9ecec40949f0bd3c0f717ef5cd58be8e83747c + bundle-info.yaml: 9c514ee86c22b13ecbd6d78583d87c42ecaf703f55b0481a324b73424d452db0 + checksums.txt: a97a275c171b6b3d59c36b05e26365b3415c04c8e4eb7b23a5914c0440e94c03 deploy.sh: ea70804cf5d8c0bb716ccd59ea4a31a1037672453aa11e2e2bfbd20daf55d901 - recipe.yaml: 0f7d86bd9c759548abf944cab2d28b2e2e9416670ed6c10c240dca14967474a1 + recipe.yaml: ddf59026c2adf9cdb001b43d1361ebc4ad8ee40008381ec16b9567fde59e6de8 gb200-eks-ubuntu-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -897,7 +897,7 @@ gb200-eks-ubuntu-inference-dynamo: 016-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 017-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 017-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 017-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 017-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 018-dynamo-platform/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 018-dynamo-platform/install.sh: 26f4a6ece285df70c933829cf3fc476fd3b61b711f858d86dd77f5abb22bee24 @@ -916,12 +916,12 @@ gb200-eks-ubuntu-inference-dynamo: 021-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 021-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 021-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 7d812ea5dcf6bd12128bdf94ebd300306eccb146814de5ff0a3998833f151a0e + README.md: 85d1a6b5cdc942f2f8105bbba98710dd91d2f437177f0aa18dbc0a3024c02e7f UPGRADING.md: d27ec18c5dbe463bc50dfdde771821d0a717e350be36a89f87297ada543ba81c - bundle-info.yaml: 441da0c5ae961abe27cba8c07bcc12d51fc9869b1159ace189e2ca7a8729a63f - checksums.txt: 043f454553883ffa5adf31a96535ef71f59e6d0acc2f3d867ad6b6684661a0fb + bundle-info.yaml: dac72fda97a10373b3fc91e5cdb8eae48cf4dabcbb74ec9710b424d0715206f7 + checksums.txt: b88412a3dc9af707fa5d4e0b26f7623d9a8a05ab70e9582ec591174f78e1390a deploy.sh: 7a305353d31349834943e912d9c671f1e44a3b9ec914d8862017d7e56dee9a96 - recipe.yaml: 99016877d03d3f8badd84640e47e5f1b4dff71d45e2fef3da6c2769064805175 + recipe.yaml: 293f0e485efd2a25dac5d9759fabd49cee995707d02e212d5d151282ec319009 gb200-eks-ubuntu-training-kubeflow: 001-aws-ebs-csi-driver/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-aws-ebs-csi-driver/install.sh: 4b3958a35a18427b6ccbefa30abdad829b99178677311ac444eff3e34c6479c6 @@ -971,7 +971,7 @@ gb200-eks-ubuntu-training-kubeflow: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -995,12 +995,12 @@ gb200-eks-ubuntu-training-kubeflow: 017-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 017-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 017-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 43af1d677a691a4e8131ef67fa50deb7921d9fedbe0aae6a941a990cb2fe0a44 + README.md: 2516726dc28e7aa023d6090a55903029dbf33596b3bb020f6501ca3dfb78a544 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 2321ed37c5fa7add302079333778e6c7eba3d6f152d59603d69389a0617e5857 - checksums.txt: bdfb35553255177fe8a7b05916068c0a9f64390da25603acbb50ba76b5e006d2 + bundle-info.yaml: fcef5d50689a4e41cdca18ec76f7b3754e7a511eea902ed35c656aa0456eea75 + checksums.txt: 2bdea117e4f00b15de4c9c214e340c0f73f697bcb549c3443aa38eeea0ec4503 deploy.sh: 5b2acd33c456f23e8d1f4d574f94b9ba2bce52147876f165a54e3395e55de09b - recipe.yaml: 4fe166f7e3189c7a81eee37ba61056a17f722ed79501c376c5ec4dd65014f956 + recipe.yaml: 0886d22dc4f22b45dfe406d3906e0f8838976c641e6d5ebc72c6d04e5a63d8d8 gb200-eks-ubuntu-training-slurm: 001-aws-ebs-csi-driver/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-aws-ebs-csi-driver/install.sh: 4b3958a35a18427b6ccbefa30abdad829b99178677311ac444eff3e34c6479c6 @@ -1050,7 +1050,7 @@ gb200-eks-ubuntu-training-slurm: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -1083,12 +1083,12 @@ gb200-eks-ubuntu-training-slurm: 019-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb 019-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 019-slinky-slurm/values.yaml: 36b3e905ded091f970dd6ad98389be8e4a6481afffb6682b66370558fa99a393 - README.md: 3fa761f45ca96954b4610e1a44e9ee4dc63d1e0fd444b9d7230ea92f337258e5 + README.md: a67565f162cbec204b619b21a95e575d97b4fd424389dcbb0b42f6294644fe38 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: ed5acd5680a95d06ced55ae4de50b14aaaf19dc069e4ad7bf573366d9967fe58 - checksums.txt: d1e2534ed16e8835cd9eb2b44b7c60652f798a6689b351301a3eb165647e4932 + bundle-info.yaml: 3976352bc085503a9d7e1a5446536016efdd68e9f084b85f7171803bd8600608 + checksums.txt: 9cd38576d8bd5d7f0d9ac6736bdf885ae56770aac70b70a3da98839d3189a6e6 deploy.sh: 3bf1475ef39efa155a2cdff6c99ffeba55d931adf38871f8bc74467845584eae - recipe.yaml: 36769eeeb1ec16f6b5371fe31c82024a55ff0e0d2b2cadb0ac6687d399655bec + recipe.yaml: 3c8bd9e1b131cdb9f5aeb450fb15648ebd193bc039b44e67b87b45ff1997d75e gb200-gke-cos-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -1163,7 +1163,7 @@ gb200-gke-cos-inference-dynamo: 016-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 017-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 017-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 017-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 017-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 018-dynamo-platform/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 018-dynamo-platform/install.sh: 26f4a6ece285df70c933829cf3fc476fd3b61b711f858d86dd77f5abb22bee24 @@ -1187,12 +1187,12 @@ gb200-gke-cos-inference-dynamo: 022-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 022-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 022-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 0f883b8cf45ab50d6e046d71ca483e90a9133c0a344b384328d4bbd9a9ae0da5 + README.md: 3e29f873111a3db0b9e7d8cd8d422e1ca1178ad7046c6c7017b29d3f2562f468 UPGRADING.md: d27ec18c5dbe463bc50dfdde771821d0a717e350be36a89f87297ada543ba81c - bundle-info.yaml: eac5f1b4ca396596923b1a92a4cdd3769773fa41d47168210946188eec55e03e - checksums.txt: d88489ee25679ea0091e9b4d87c11c731a21f1bf6a3adc3e8abc86bf9022f989 + bundle-info.yaml: 63467450764ac1199f805f751e86dac039b6d5433ae7b5758a8902e09f1ffe9a + checksums.txt: 35d7db714d2ca5bc79bd50a17084c7b1587431333514efd58ac6f040e73e6c3e deploy.sh: c27046f23c79d92f9cdcc9725b9ef25978758818975807ba376dc5e6f9fda214 - recipe.yaml: 9cac37bba449e4309e64f0926ea3b48296310c0dd6f5002760697b9621c33576 + recipe.yaml: 078a741a1d327d3f6210f2d0eef7801338afbbae5778a827eb0db5093a076175 gb200-gke-cos-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -1244,7 +1244,7 @@ gb200-gke-cos-training-kubeflow: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -1269,12 +1269,12 @@ gb200-gke-cos-training-kubeflow: 017-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 017-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 017-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 9f72f7c976888ac46558f3a26424107314227af1a20ecc23e28fd9ea212af575 + README.md: c1c1f3e6b0d11d70992390e154f6b9260198aa011ac392ece04f00467e1de662 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 8c5b3d8800aeeff6bc4ddf607b0ff9ef49b20eb95159a3641226ffea26063677 - checksums.txt: 7d5b7b2fc417a8d1f6cd1137cece802fbc5a44b39e0f8a54342f05313f2ad652 + bundle-info.yaml: e85c313290b1dd89b7c18a23ece59b85b8e0452ae1dbdfa8a7a16daf6ed4044c + checksums.txt: fc8ab16d25a4c88509599c041d4c070055e4c666edf0dbdaad318a56ab79d955 deploy.sh: 7d1e5335991335299686c41cb44d9609d4ed3b5aa59506a38dd64949a2553c54 - recipe.yaml: c2fbdbbe659d84d23e21f9da54825a1ec83e37139e26feb9c2592fef5af42ed0 + recipe.yaml: b740db98bf036aad744770502d7fad80bbc04b08b464b5d43801731383fa61cb gb200-gke-cos-training-slurm: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -1326,7 +1326,7 @@ gb200-gke-cos-training-slurm: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -1359,12 +1359,12 @@ gb200-gke-cos-training-slurm: 019-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb 019-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 019-slinky-slurm/values.yaml: 36b3e905ded091f970dd6ad98389be8e4a6481afffb6682b66370558fa99a393 - README.md: 86ca6a2e60ef1ce0b5bc9ac9a5096a956e9ac0bd8e4cee2755c8509f5e551425 + README.md: e1d1f9db82f9deb994b3bfc8669423e64042e7ab3383b7c07f955dde9e1dfde1 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: f9621467f7863c82a9587f31f6e5e442de91a6c3c220182c15406b046ad52e61 - checksums.txt: 47b034b40186b5b1f80891d9a1c00278bd16e65614d4842a2a7595e2d38623f8 + bundle-info.yaml: d25e99fc63b0e456b40d269cf8c82f791df17b165d97ec91ca0e7ab4928c952b + checksums.txt: 7edc607dfe349164f9a0d2dfd4f009c0161161e2aad140dfadc58c6dab5ed105 deploy.sh: ef955644171896a717b59c2582b0fbef5b6cab0d2f67c89924656b3aee005c73 - recipe.yaml: 1bc779869631a37d7bc3cb49313e57bc577f8aa0a99ce4992dddc968564910bc + recipe.yaml: f0801facb3e7fc66ea710e20ca48788b2e3aa0748c0bc245bb8f31665a08eba3 gb200-oke-ubuntu-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -1419,7 +1419,7 @@ gb200-oke-ubuntu-inference-dynamo: 012-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 013-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 013-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 013-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 013-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 014-dynamo-platform/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 014-dynamo-platform/install.sh: 26f4a6ece285df70c933829cf3fc476fd3b61b711f858d86dd77f5abb22bee24 @@ -1438,12 +1438,12 @@ gb200-oke-ubuntu-inference-dynamo: 017-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 017-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 017-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 6242517b67ea219b0acbe46ed9c8f1569eba35255f82532c25446030a7eea85d + README.md: 696a477c1793905702565f42900bd07293f5dc0427720ce4caa78116d1acb084 UPGRADING.md: d27ec18c5dbe463bc50dfdde771821d0a717e350be36a89f87297ada543ba81c - bundle-info.yaml: f369d8bf5acb55840e9179d05230aabd42c25e87b718adc49fb54adb531f8cdb - checksums.txt: 1aa423dd42ad6833b8de79a9b2788f570cea2a16c9647ea2980f1be3fe59aa0c + bundle-info.yaml: e7731d42d6253ee3a491157088972a54e3b953a9627c350553d4b0f15a0add4d + checksums.txt: 296f2f7b5932c977e39a5374a6c72e23b9078d128af07ab9216654d1254309a2 deploy.sh: 6c9407779b830bf0997644af6ced980afe20317b576ffc024df41eb719b8d949 - recipe.yaml: e3a1bb44834e5b242e5e6b2b7be04c29b4d9b106e292d90ce47d52a1ae582243 + recipe.yaml: b7734c45b9760ee975b55790baef5c6077018e407902499a11776adabafdd718 gb200-oke-ubuntu-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -1489,7 +1489,7 @@ gb200-oke-ubuntu-training-kubeflow: 010-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 011-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 011-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 011-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 011-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 012-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -1513,12 +1513,12 @@ gb200-oke-ubuntu-training-kubeflow: 016-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 016-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 016-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: eeb441534e6dac00ae0c4262b729b23be1148be66f9602bd85cf82aba605fe7f + README.md: 88400fed3e4914cd52f6b62fdfeaac9af6b5586ae45b7af3ad6ab34441520571 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: bd28c90092298d3cb527df155396b31adb575214fd90e8e381ef888cdbdf400d - checksums.txt: 25a4383f42ce818758b79c89bbe9d63b71dd3c1adf9096ea8c445fe4e816d50a + bundle-info.yaml: faaf7f0e8e7642df777b489a51afb534a3f1580b7790a8376ab362669b514738 + checksums.txt: d0d3d77fa2114e54184e48d145833e69239ea44405634e458150744d00d80be0 deploy.sh: 83fa4613633138d6b344997098cc0b2f77082f6fc1ba1cca6cef729b1a316cd3 - recipe.yaml: 533380c82da0b4dbda99f3b5d744057c82fb7ccdd0a470b05c65bc29671059b9 + recipe.yaml: 187421acb4178455cb4f5bdbe88784c0693d83c721e0ca22c2e55703b8fffb7b gb300-any: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -1550,7 +1550,7 @@ gb300-any: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -1565,12 +1565,12 @@ gb300-any: 011-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 011-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 011-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 3ef7ab2055833c836afe728785e2d1c477e22def8a9087b5ac64f60e5593eb6c + README.md: 04b63b2b4103852fcfefb00cb9bf4cd2ff990ed28e7e8d57bc325320bdc7196c UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 812ec5168e9be198310acde61285650d43964ac9bc0bb3dc7d5c336e87eb658f - checksums.txt: 3cda8f96de5948165e5ac5d771f3a265af09da16f8cdc4e8dd5770e60c506198 + bundle-info.yaml: 6687d05d90f17b57e9d971476be2c0899669a54619ab4b863b3b5038c1f96064 + checksums.txt: 2dcb6ca845b41e96146fd3455f9e9be2fd66c67054da9812665a6a24878ad8b7 deploy.sh: ea70804cf5d8c0bb716ccd59ea4a31a1037672453aa11e2e2bfbd20daf55d901 - recipe.yaml: b77d5c4ef355d75f0c9b4999f0d57b3d5ff426f78cab48012d0eb1815a037394 + recipe.yaml: 81c3ac15c21d8066c7ff255f0348ed4c4778fec99f8077ec91f6c3c6259bcebc gb300-eks-ubuntu-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -1643,7 +1643,7 @@ gb300-eks-ubuntu-inference-dynamo: 016-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 017-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 017-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 017-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 017-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 018-dynamo-platform/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 018-dynamo-platform/install.sh: 26f4a6ece285df70c933829cf3fc476fd3b61b711f858d86dd77f5abb22bee24 @@ -1662,12 +1662,12 @@ gb300-eks-ubuntu-inference-dynamo: 021-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 021-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 021-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: a511d3e61c3f67f76df9ab26a2a7f5d4cc5343993dc96374b2de60d3b1ea3e33 + README.md: 0430952fa5b04b154fc5b85f0b8a10ebe4f597e78a529bf036a267aafe55477b UPGRADING.md: d27ec18c5dbe463bc50dfdde771821d0a717e350be36a89f87297ada543ba81c - bundle-info.yaml: 616d719558836e403f23137366f5a49ee112bc02ca55410f0376dabf126dbb49 - checksums.txt: 5c25e708e55ffbd9d51e814c765f7c89996d51631261156517d157255878ad1d + bundle-info.yaml: cd109c0ad4fa2f855e0fab52e667614a8393dc5f8d18bfdf2aa07e3299990f53 + checksums.txt: 134998f24b443335ddc3ad6cce04f6260681cae4bb7bac50b18327b86efaf1b8 deploy.sh: 7a305353d31349834943e912d9c671f1e44a3b9ec914d8862017d7e56dee9a96 - recipe.yaml: 4aa6f0d612c3e364603fa25a8e3e3527c203f81736e5cecc718828a9c2c98d60 + recipe.yaml: 11ff37e20bf26f62a874c3d1f62c695570f195d3fb588a9224ce98d990fe18c8 gb300-eks-ubuntu-training-kubeflow: 001-aws-ebs-csi-driver/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-aws-ebs-csi-driver/install.sh: 4b3958a35a18427b6ccbefa30abdad829b99178677311ac444eff3e34c6479c6 @@ -1717,7 +1717,7 @@ gb300-eks-ubuntu-training-kubeflow: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -1741,12 +1741,12 @@ gb300-eks-ubuntu-training-kubeflow: 017-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 017-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 017-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 6e06975e1ff735dd78f986ffce4e16742dfd8b114f8427bfb149570312465292 + README.md: 8edacf4bb0f7705b03852468f54f2663d70e4a3798b77a2dc5d9e69d905f00c3 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 1d30e69141e264a6cffbbfc0199baec719fe3694f29e1af99c55a222eb52af73 - checksums.txt: c6d0235d2666496aed8fd54cb2919df529e455483a31113a4697031b5d4f3927 + bundle-info.yaml: f43ef320acd010a6be75c890b200d289cf50dcb606089d62b28c7033d54310c3 + checksums.txt: 14992f6da4a658c995d6f14e236a2ac4ec8e18fc67ffd209dfce26cb15040b01 deploy.sh: 5b2acd33c456f23e8d1f4d574f94b9ba2bce52147876f165a54e3395e55de09b - recipe.yaml: e017dd3bf35f86f1e94d252ae6dd3ad95726071726d3c99530a6899e3a412b66 + recipe.yaml: 267f5dbfd0e35e3d9860ce9c020836de16398717aa82cbc58b9a32653f1ddc5e gb300-eks-ubuntu-training-slurm: 001-aws-ebs-csi-driver/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-aws-ebs-csi-driver/install.sh: 4b3958a35a18427b6ccbefa30abdad829b99178677311ac444eff3e34c6479c6 @@ -1796,7 +1796,7 @@ gb300-eks-ubuntu-training-slurm: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -1829,12 +1829,12 @@ gb300-eks-ubuntu-training-slurm: 019-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb 019-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 019-slinky-slurm/values.yaml: ef75bbe2e03bc4b1cf4c4f4456b31d470a7bcce3ca243af1891f9dada650c6f6 - README.md: e68c8b287f190c56a33b6a72d098110a878cb9a52ad70f8ffc521662fb1cba8b + README.md: 6b3aa42e2d95284719b6e4b01b7c59a59c8cce2cc133c4ba8aed9c44c243e8a6 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 8997a0e021a97fcd4ec0382679820778200c399bf66554c4f2c842f8e0657705 - checksums.txt: dd4811e996e6d0c9a9ae16b0651e5dc6e8852933463f62e17871c45b27f7b468 + bundle-info.yaml: 64e489b3720c45ec9533101230ce7dd875800865ac5b92452e03110a755b326b + checksums.txt: db66ca28c834fce3229de748312d36bd25e74931d5c8ecaad8a2605e2bfd85e3 deploy.sh: 3bf1475ef39efa155a2cdff6c99ffeba55d931adf38871f8bc74467845584eae - recipe.yaml: e8ae72ec3e1bf9e91198a0246ab80e8d534994d995c475511a2c4f5f80e48e53 + recipe.yaml: acef89d3c6fcfd2a27d3ac7af935c0782ab8b76a4c4ddbc1107fc1d34f881604 gb300-generic-ubuntu-training: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -1880,7 +1880,7 @@ gb300-generic-ubuntu-training: 010-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 011-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 011-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 011-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 011-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 012-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -1895,12 +1895,12 @@ gb300-generic-ubuntu-training: 014-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 014-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 014-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 220ee0f077375a93701aa20ad10fc325d5a2be5c6cb5ec0d56310de4c5a7f2d6 + README.md: c755f209d22800215b19cfbf9b78d8a4e2a070b276ff2ac928ef80c55ead4cea UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 01c4c17f8cfb3a1bc3b5739ec81c5922e2ade03f6115fb447ebb4361741f10b9 - checksums.txt: 261a4892c756ba9b26d130309d520c04b0d86b59411d321fc544fe4125b073d1 + bundle-info.yaml: 4bf990b04aa977ce2b028fe59af212e1685f827da687cba104ce5973372013f9 + checksums.txt: f8ba79269d38505bc05ecfd7c7a9663403ad450f19b9d75e2f7e046e8c7feae1 deploy.sh: a4407de071637cc7bcd2e67d43c3d51bc767423e6200467a435e1898f67b0627 - recipe.yaml: 4d69760384d18a3291c6dc0a5a20f8e0e3ecff9fe814160861beda5c0b984376 + recipe.yaml: 3128bf4aa7b1a4837095c7e64f2064b880a330aaa28bd4c4ffa420b603e89a59 h100-aks-ubuntu-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -1976,7 +1976,7 @@ h100-aks-ubuntu-inference-dynamo: 016-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 017-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 017-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 017-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 017-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 018-dynamo-platform/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 018-dynamo-platform/install.sh: 26f4a6ece285df70c933829cf3fc476fd3b61b711f858d86dd77f5abb22bee24 @@ -1995,12 +1995,12 @@ h100-aks-ubuntu-inference-dynamo: 021-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 021-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 021-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 8ffffac5dffea4fc5493a5d2144bcc4f819304c71f4b0e753b2dfcc53d88c224 + README.md: 7ceff59317905c59fe180e052dbb712593f392016b4cbe1fe7fb79137244b32c UPGRADING.md: d27ec18c5dbe463bc50dfdde771821d0a717e350be36a89f87297ada543ba81c - bundle-info.yaml: 5dceea0a0f68d6247bdd12ae8a53cacc738a855579503a44235d58c27ed68e6e - checksums.txt: 9e134c598f981da5d91058a3bd4834ea965b0decc37aec4b003cc5ccf8ac2b6a + bundle-info.yaml: c7e56afd611c36d470ce5b6f1d64deb2f4e67db09876c7b36e52f782f9885ccc + checksums.txt: 0f5a2e7388fa9ef0ffe8db169e3186964c524be0af36dde9b2092e9f987241a4 deploy.sh: 8fe244abd3dd37ba57ffd0c551fe092c6c2c7fe033799da927170855d0104583 - recipe.yaml: 91155a3b152a7efc742884990e01075f0a0a42379f75fa92d08dee0e9b89fab2 + recipe.yaml: 78ebfec8ccb514b5cdfe894c2bf0a271aebd32ba003144d426870b819a7643e0 h100-aks-ubuntu-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -2053,7 +2053,7 @@ h100-aks-ubuntu-training-kubeflow: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -2077,12 +2077,12 @@ h100-aks-ubuntu-training-kubeflow: 017-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 017-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 017-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 62edf7818cb89a0d4d40a9c6ad451df97b7664ea01b23bee64403d3c47a8b406 + README.md: a795131c421a59a91987f350504df766128eb4780e8bc653da30d0f5fc940e26 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: a4bc974b5a744dbd68200b2c840b8c21feefefd36afd3a676fc9419878383579 - checksums.txt: 3912eec5a32e70a5b21298ac12a2272303845b8453913e31e184010b2a2e1941 + bundle-info.yaml: e50a27bd53b4a5a9615ac3961cdf81357f9154c63693c2f6aca1acf093ed809f + checksums.txt: 17bfaf13777b95c54a58bf3ef7e899698ca20d23a5a6233f3e844a5fd2be8b97 deploy.sh: 578de8756d8c7fd3f4cb092af39adaeefd0e3df50e5d248893b42bd1029f4532 - recipe.yaml: ab935ef631c32798d5680c1c2e2c770cb4eff3534e19a87efd41a544e5d86ef2 + recipe.yaml: 131e332699130d91b7a464de0168d6e4b04a6377b85516b3ce29e9121e8fa26a h100-aks-ubuntu-training-slurm: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -2135,7 +2135,7 @@ h100-aks-ubuntu-training-slurm: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -2167,12 +2167,12 @@ h100-aks-ubuntu-training-slurm: 019-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb 019-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 019-slinky-slurm/values.yaml: 5643ef72841c8424adbe75cfb40f99691ec60c5e6498bb3a115824a3264bce9d - README.md: 07cb6a0cf061ee1d2901ca0e90f4b9617e9a3a56cd863fb28e975e1aa5f6236f + README.md: 1e9d7171899b1b8147b29f1cb0b0ed5780879fd179f87c3b1f3d0dd1c85bf0af UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 50d6742738257cea4b602afcf67b7d1b99e85b3491257b10f6b6eb8d9fd65181 - checksums.txt: 3ba316c8714b057d4be855f3ac1838dd4793754a0e1502fe23b43660dd06b320 + bundle-info.yaml: f10cfec0f53deb798aa9bf1a92cd9bfa20ad7c665decfb01295652c34c12aae2 + checksums.txt: a983fe2d672271ad21c9952b4c27969a99018c8014413f58a0bbe2816cf2ce1c deploy.sh: 9b4d0619afbaa1425c76e4035df5a7a41bb8c10f35fd0892b7e552a3bc72d66d - recipe.yaml: f7bc433711c19af1be05a9ff9625276a3c6f1672931c629c48a189b5d89c409d + recipe.yaml: fc985d34d89743c0006f2f39f112e71cfbb9bbbd7513e57c02e631605c3298ad h100-any: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -2204,7 +2204,7 @@ h100-any: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -2219,12 +2219,12 @@ h100-any: 011-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 011-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 011-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: c9c17733e6903e0c364122d669a050b87e7a5ed1aab5ec25cf28806e7216ebfd + README.md: acd8a3fa96535c7418ebf0bd222393f1e8862aeb66b9d3e8650eb648073fc9ff UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 5ae21a9ee0637c62e0c4b4bb907a63fdccf6f999ccccd67264c22f48cd423746 - checksums.txt: 54927b14ee2d9b142f34cb8a446eaf763fb2b2f59a3bf7f708e8563fe1579709 + bundle-info.yaml: efdd7a3d0327f09a7c5291d025d6607d0df117760d29c9bae7f885b1c7a7a852 + checksums.txt: 93fa77a456b3e01ec40c5624e787088a5ebaf035572534c6d2e0c847d43fc571 deploy.sh: ea70804cf5d8c0bb716ccd59ea4a31a1037672453aa11e2e2bfbd20daf55d901 - recipe.yaml: 2e0d488d24e987f116cb37ceb665dfef4df87ecc0018a0777337cf9e052ffd4c + recipe.yaml: 632ed1d58f891e71cb7967f537939d48c0075bad1604f3891949182a2983e9cf h100-bcm-ubuntu-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -2261,7 +2261,7 @@ h100-bcm-ubuntu-training-kubeflow: 008-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 009-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 009-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 009-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 009-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 010-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 010-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -2285,12 +2285,12 @@ h100-bcm-ubuntu-training-kubeflow: 014-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 014-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 014-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: b948a5b9a3a419f5208de7f79d9ae81a73cbdcdced0e23b67b14ea9784207d5a + README.md: 2237f379a5dc7a0fc8c5b5f3f2c905dc59c4411c5ee33ba83f39d2850f3ea5b9 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 81601dd90ae55fa09407c5bef15c53280feb7852fabd037406171e594902f262 - checksums.txt: c10e4f159d384f1502e338566072573ba55f10c9d83de8f0945966a5beea8777 + bundle-info.yaml: 833573a4a94c5ef86e897a22825a48bed681257d29c73fde43ec3a01022c5e7b + checksums.txt: 9beb6de8781cfe89a98aa93c1ab6cda652b2a51c42e35904cfda06c06f6ec148 deploy.sh: 942b1194469de9dfc1e8b55420980e47fb7cafa917ef628d29af8817dfbd9d79 - recipe.yaml: 438a504c7b781356509eae930652b5db7413d8fd188b0f553fc6cb7a063c561c + recipe.yaml: 661bf4294e1ffe44f80b5b28ee0da03775c7a799503e5f898f6697cb23b06dc9 h100-eks-ubuntu-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -2358,7 +2358,7 @@ h100-eks-ubuntu-inference-dynamo: 015-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 016-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 016-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 016-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 016-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 017-dynamo-platform/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-dynamo-platform/install.sh: 26f4a6ece285df70c933829cf3fc476fd3b61b711f858d86dd77f5abb22bee24 @@ -2377,12 +2377,12 @@ h100-eks-ubuntu-inference-dynamo: 020-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 020-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 020-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: af590efaa7ca1d2760af737fa973ee54e7cfc273529f94b7fb08170f1ce70c4c + README.md: e17efa032da7845467aa675a61bebaba82da3e1b8125f636655e967c61088ad9 UPGRADING.md: d27ec18c5dbe463bc50dfdde771821d0a717e350be36a89f87297ada543ba81c - bundle-info.yaml: 6fffe7c7863286b5589c835af53914ca05afccd20596e185cd799e18980c1fb2 - checksums.txt: 131b82d42932e40287d6a61e17196aed80d169241505d7ca6382bef58ba1299c + bundle-info.yaml: 9f632149a68f6e37d2249bc0a5620116b821bd90285162886f83c73b87c82607 + checksums.txt: 6dc7a03ea87b9754acad2015d9d28a9bc74d7fca62505b10df63153cfb393fde deploy.sh: 7a305353d31349834943e912d9c671f1e44a3b9ec914d8862017d7e56dee9a96 - recipe.yaml: 8162d79cda156236cb4078ad712d927ec88f954fadf3d2c60edbb77deae6e688 + recipe.yaml: 51c87d66719a7c2af40ab577a93922926cb53e3a5424ef8f2f8b3db952360cbb h100-eks-ubuntu-inference-nim: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -2450,7 +2450,7 @@ h100-eks-ubuntu-inference-nim: 015-k8s-nim-operator/values.yaml: 09dc1eb39d26de0971d5bef591a61a7faec57c01f09388407951b8b4733fcc53 016-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 016-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 016-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 016-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 017-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -2465,12 +2465,12 @@ h100-eks-ubuntu-inference-nim: 019-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 019-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 019-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: b65217878628ebcba2f35f8006ee24ccf705434f0a794d749edb384c367f25da + README.md: 14166924b0a4103dc5406663dcb774448884ff57cf3a6f4d3ba98288a4015f9e UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 7c006a7f70694e0539479a2f137418328306c4e73d4ab016f7b52f4e86c7c013 - checksums.txt: 558b8bdc0a4bb5510976c4a2dbf9fe8bdc7d2b1b79de4fec92385478c8786c6f + bundle-info.yaml: 794913833f2184fcd6f39896eb39088c393b15daf0aa61f77b24bd8aee2d9f80 + checksums.txt: 36553c2ae5964c97b60ab0fa39aee4e8c9bb1e12f17796a1a5f1a1d32e810a72 deploy.sh: 038181d6586cb77d4ab6094a7ddd94e9db4b9c73160da7aa5f13d7389f5166e0 - recipe.yaml: 231dd0717f699e2db1b686a097dac7b637783b50410d3361cb73dd73bad3b8a1 + recipe.yaml: be731ae583ecd3a52884912fb9fa031ab659233bfa810aabde1894eae1e99f7d h100-eks-ubuntu-training-kubeflow: 001-aws-ebs-csi-driver/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-aws-ebs-csi-driver/install.sh: 4b3958a35a18427b6ccbefa30abdad829b99178677311ac444eff3e34c6479c6 @@ -2515,7 +2515,7 @@ h100-eks-ubuntu-training-kubeflow: 010-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 011-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 011-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 011-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 011-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 012-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -2539,12 +2539,12 @@ h100-eks-ubuntu-training-kubeflow: 016-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 016-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 016-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 4993cbc00e197f69746b9d2688e3e3f3afffaced1053d030997a7b71564a014b + README.md: 0a430056e7ad10d718a27aca337eedee3b16654ebb1050dcd2505fd7b7eff3da UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 9e27217baf0328163053412a9ec906133043721593b1123c1fecd6ce33e58881 - checksums.txt: df791557f6a8717b23a1fabc9b65f862ee31f8ddb5385a21c57fe3bd119fa5ad + bundle-info.yaml: 2810016dd44698bb2089eaf58a46211abefd8c9fe678a42675f3198c759f8e4c + checksums.txt: 1f9cd64a8bda800bd7805acfe290945306be45d544ef697c1b3ebe9b7c71fe75 deploy.sh: 5b2acd33c456f23e8d1f4d574f94b9ba2bce52147876f165a54e3395e55de09b - recipe.yaml: df5b2f780667e7d3d5987ad6aa76cc470355b84800dbf5d1f6ea950bdad4b027 + recipe.yaml: 6c1e1b34a6019b5424ac6f038cc69a9cb09129ea51881df0299e9acd6097cf0d h100-eks-ubuntu-training-slurm: 001-aws-ebs-csi-driver/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-aws-ebs-csi-driver/install.sh: 4b3958a35a18427b6ccbefa30abdad829b99178677311ac444eff3e34c6479c6 @@ -2589,7 +2589,7 @@ h100-eks-ubuntu-training-slurm: 010-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 011-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 011-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 011-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 011-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 012-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -2621,12 +2621,12 @@ h100-eks-ubuntu-training-slurm: 018-slinky-slurm/install.sh: f8fc21f4d86df489d9fa6f5492e84954826b7dd5944b6e1e494c5e27e9ba20eb 018-slinky-slurm/upstream.env: d6d98698e039f356ddd432950fc6550524f2621d0f12f9a1fa2a27b53f578643 018-slinky-slurm/values.yaml: 5643ef72841c8424adbe75cfb40f99691ec60c5e6498bb3a115824a3264bce9d - README.md: ba0b430277109b5233ae3840444a9476be08c6fc81e2136a02f88e16d5c38b51 + README.md: 3ee053b7c60e39668f3eca4d87e3cb2decbff27e94e078535016e38f8164ec10 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 1d6e9a4033002d08ff08028039b6afb58544f074a22113d51ae024eeafd06b02 - checksums.txt: aa0d34d3086823fe77e563f649ce4a8699c5530ecb1e783fe4a753b6c771f769 + bundle-info.yaml: 6f4a93ffdc3c1d1f8b4751a7db63a6c11b046df01ea08eac20e5c551c22db737 + checksums.txt: 08c1c66fb4da28a4c9109151bf1a8469cd978ec1ce77f06c88d0a63a0e50de2b deploy.sh: 3bf1475ef39efa155a2cdff6c99ffeba55d931adf38871f8bc74467845584eae - recipe.yaml: 62899b14837be9c736a686a2ac9f46a0c32e081991088797e5102dcaa7899b7f + recipe.yaml: f9ab75b288f1d5c4d72e49074f0b6f9c9706d3c1594aca780f3d026612f536d2 h100-gke-cos-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -2695,7 +2695,7 @@ h100-gke-cos-inference-dynamo: 015-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 016-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 016-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 016-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 016-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 017-dynamo-platform/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-dynamo-platform/install.sh: 26f4a6ece285df70c933829cf3fc476fd3b61b711f858d86dd77f5abb22bee24 @@ -2714,12 +2714,12 @@ h100-gke-cos-inference-dynamo: 020-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 020-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 020-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 0816d3e944d74c218fcafa501024c8fe7cabd7a6834db08f58094e4d62e3f7e2 + README.md: 5efa5a9c6e6117b86135377e1dec1b7758717fe514a4912d480cfc9ee9591e3d UPGRADING.md: d27ec18c5dbe463bc50dfdde771821d0a717e350be36a89f87297ada543ba81c - bundle-info.yaml: aee2fd047e41143b9e2d7b18704875d0f40a77bfaedfa17cdbea2a399eb28d50 - checksums.txt: 86221bd5d33eeb9847be560a82a0f252ddf4701445df45b517921c6e95ccdc02 + bundle-info.yaml: 78882de23f2d309c22eca758314717c83bcee6a1b1f3c4e62271f239f8f34c9a + checksums.txt: 70558e5e5d859a3fdf0d80d580e72a8def0b088af6c2e2b2964987d09ce7860f deploy.sh: 62b3ab91044223177c74d3aee7241f4aeae64e6bdb31481f7da642dbf4556e9a - recipe.yaml: b1134834618a00ab52c1450588179c15228c089715e79d1b45fe325c4e7d2165 + recipe.yaml: d4ccf503b7ce233f553bffc8417e75c59b6dfea8c7bc7dd755299af996728de5 h100-gke-cos-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -2771,7 +2771,7 @@ h100-gke-cos-training-kubeflow: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -2796,12 +2796,12 @@ h100-gke-cos-training-kubeflow: 017-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 017-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 017-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 720cf3194fa2d25b9f7c4f751a09225a836b8b3fbaba9129a12636043eae6db6 + README.md: d17a4b31629bf47c13548f2c47b2c69ae449d085c34f5131ecc0c6678d9753b8 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: e5d30a9b0c04b614ebc00788765f4f7504e9a6312656da531624db7c89e81cce - checksums.txt: 73ca430580be881db1dd7af98ef73949b0b8e02904075f5b4821decdfdd4ea8d + bundle-info.yaml: 6f3f0800313b0e829fc2c08250b79d30b72a7f034405fc48942065050604f8a2 + checksums.txt: f43601abde4ca1a482cc0fcb266b2f231ab85a8085fc1155fb4c6454be9ded75 deploy.sh: fdb5b08014a89062f4b304cce41d91410d4a690f2c5a723cdb4b08028097d92d - recipe.yaml: 00c3652a4b3ac832d31a2eba90101a452e15e5fa5d76fb03df81c3097c8d2a69 + recipe.yaml: 03246d4b6aa9d2af0861cbb81aa9db0a2ba2c2fcef52512727e0247e966c3319 h100-gke-cos-training-slurm: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -2853,7 +2853,7 @@ h100-gke-cos-training-slurm: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -2889,12 +2889,12 @@ h100-gke-cos-training-slurm: 020-slinky-topograph/install.sh: 19c15d32f7578504e561768affa18c21390db951c791a33998fd2bab58a881d8 020-slinky-topograph/upstream.env: 1b99e05b70b8b6b7dd457a99b2e29f9eec8b6244d1854aed0c416ea19a3e62af 020-slinky-topograph/values.yaml: 433c88d6355bfefd023c111e008a39e7c07c913401708a2641717ca5a796a1dd - README.md: 03fc04c4998661811fa2919d7768f96e45d24b49de8d11c96dc510b4a9e473c9 + README.md: 30d0168c55ceea47078d2083715501a4ca8088bdcfca7a0ec0494932e058edba UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 30af4e250d05af785988a972fef49aad9a0446dd77385186509eab23c56cc60e - checksums.txt: bf72d8ebad6fb65d350a92a6e6f035e080920ac25152db81fc4b440b54ffb4a8 + bundle-info.yaml: 64f74dfbb253e6215c4bdc65af58eafbaa59f895d0beae7385a01b1258aebebc + checksums.txt: edac1c3d2c8c542cd0560a2e24a9f7daedc9cc1c43b41404cd4cf70bc23d3411 deploy.sh: 26b5bbeba08ab0830741d513d86fb9b24a204d48968b95c88fb5eadc9fe67cba - recipe.yaml: cba343a404f486044d2210e877768fefe4126b9a17f9322fa5a396c13efc8f3f + recipe.yaml: d186efcc2a449b4f708b98db1e19363a3e54451d242dd2d1cd24ef8770410036 h100-kind-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -2953,7 +2953,7 @@ h100-kind-inference-dynamo: 013-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 014-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 014-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 014-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 014-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 014-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 015-dynamo-platform/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 015-dynamo-platform/install.sh: 26f4a6ece285df70c933829cf3fc476fd3b61b711f858d86dd77f5abb22bee24 @@ -2972,12 +2972,12 @@ h100-kind-inference-dynamo: 018-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 018-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 018-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: ab9eb42e715795deb1f8ed539ee4a8a7a47772beb80fee3fe11ee30c298f664e + README.md: 580b5290b5db8ca5a0362914e9886376d05428a2c9f3f6533ebce0706f0628ae UPGRADING.md: d27ec18c5dbe463bc50dfdde771821d0a717e350be36a89f87297ada543ba81c - bundle-info.yaml: 3b1624a1f0e84de11b081953baa4ba2d15d386ffeb6424227b04e2e4832d0bc8 - checksums.txt: e4543bd82ce721f567fab1b1f2bf6c41df514eda1762ba3d00758a07e0612c6a + bundle-info.yaml: fe14611d82dfc994801261b8251d52f2957c1907075834a9f9b18b65e53b8607 + checksums.txt: 9681d3ea48e5b9cd6fc7e7d4d02f0fbb203b06404f6b4b5e6853d562ca5321ee deploy.sh: 18827849e66bfdd7d103aeab9f6374a7018500f6b57a3e3a68fc789bf40ec5b4 - recipe.yaml: 8547fce134e27a15ffc64eda6bb79398e2d7f5a23a3d9a6d98829654909383c0 + recipe.yaml: 7832cdf431414483bc14ecd67222305b8f6ce6585f1c8fd15e49149ef16ab4bb h100-kind-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -3013,7 +3013,7 @@ h100-kind-training-kubeflow: 008-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 009-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 009-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 009-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 009-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 010-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 010-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -3037,12 +3037,12 @@ h100-kind-training-kubeflow: 014-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 014-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 014-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: bf5195c04e85d5dfab9768cf5ee5be7a8f5370a0272557dfa1782b84ef65bf94 + README.md: 87616fbc25db4de5c2ae7fce86b94b14a7a037264005dbc80f66ba8e236236d9 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 5d8907879020323f5cff687edb1fdfe98b6c26f7166a62517c4cfeabde9ffd46 - checksums.txt: 54e0f136ade2c2af0a3290ff89ed1fdc7017365b41b1929a2c19064259f1d03d + bundle-info.yaml: b22a7cf563cd9cb3707447dbe0cb0f3e00a55c08a47f7f94bc6cd790c38f665f + checksums.txt: 1a6130a524b902e772bf4c91c96871deb768ae4543373de8053e5e58dc281b74 deploy.sh: 83fa4613633138d6b344997098cc0b2f77082f6fc1ba1cca6cef729b1a316cd3 - recipe.yaml: e25f52da6bcb17d0d098ca48b6eaf83fde3d5030554f934870e6f4e252ba59c6 + recipe.yaml: 2f84b4449b54cb418bb6abd5311c0365cd3c24bdd5409ed1b0d33e679fa4a974 h100-kind-training-slurm: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -3078,7 +3078,7 @@ h100-kind-training-slurm: 008-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 009-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 009-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 009-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 009-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 010-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 010-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -3114,12 +3114,12 @@ h100-kind-training-slurm: 017-slinky-topograph/install.sh: 19c15d32f7578504e561768affa18c21390db951c791a33998fd2bab58a881d8 017-slinky-topograph/upstream.env: 1b99e05b70b8b6b7dd457a99b2e29f9eec8b6244d1854aed0c416ea19a3e62af 017-slinky-topograph/values.yaml: 8cc3bf52dbab729d1b71e495c8d51a58a5ea3592b18b356e4bbc0ff7b587b188 - README.md: 21af7eb79c1e695598de534bae5ec18d2de26cb05c16c8985db30914eb5481d4 + README.md: a045577e471bbc630cb45943e4070dfdcf770514c66fc592facbe5acf70a4660 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 8cb46afe6f9e348a13c912c81120765c9510bb9e4938243ea8886cff7200d681 - checksums.txt: e1bd82aea341646f0114de57f92b30ff78a98e636389a5c2272669c84da8c5aa + bundle-info.yaml: 04d6ea17aec2f8fb68f5070307b4b615d13f8c350c358c98a47eb0aa776071b4 + checksums.txt: 12498de2f1446d9b382aa1b0b249c0b05afe8a9176be0805ab44f1bfdf84afcd deploy.sh: a9268f292354d1038ae6c7401d39c2fd190aafd3e2f0f7a3820ee740e685255b - recipe.yaml: 786ff5028c4d02ebf8d5fdb9a3f5f8078196fa63136306c0e8ec93f6bb9e0cc3 + recipe.yaml: 029676c7d257e4a12028813c867ced28862b8b4d7130210d8d5d7639b45281bd h200-any: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -3151,7 +3151,7 @@ h200-any: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -3166,12 +3166,12 @@ h200-any: 011-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 011-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 011-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: b7491c1e6319aa4363c353d8759e50cf4551e524917cca63f6298707bccc11f0 + README.md: 642cae7b3ab83f1c288040c824acf60dc86d5e64c6607fcea7e7b844c68a614d UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 514837028e4e12b7355ad78abc8ec7e8375263349badd4b06e9e21513c83188b - checksums.txt: 64c76eb41171549ee79d9fffdbcf3e3a0038c11de90c0baf3f229da0bf2c602f + bundle-info.yaml: a293a4ee106fa6ef7a6deea123c575670c1f243d864132eded96341149296c96 + checksums.txt: 78dee31dcfe7d57dd58d883b43db1f572bc1811e0edf2bb70022b65829843458 deploy.sh: ea70804cf5d8c0bb716ccd59ea4a31a1037672453aa11e2e2bfbd20daf55d901 - recipe.yaml: d64ffd6cf71899c321776323620b7599b641ed934fb21a32d09e9427645f8af7 + recipe.yaml: 6c4c6a7a8581ae573a2f0d7cf3beb5a0cd8544ed0f89751c06c32048c3a36c78 h200-eks-inference: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -3235,7 +3235,7 @@ h200-eks-inference: 014-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 015-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 015-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 015-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 015-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 015-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 016-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -3250,12 +3250,12 @@ h200-eks-inference: 018-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 018-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 018-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: e5bfff423abbef94b1784b7d6557f04ff53715ba2f86dd90bbf04824ed0c5d45 + README.md: 020d9dc6243424e09e9b0f777a91052c5764253f58721263a201c35119cc6c2f UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: c04691fb7b2a50ff090141c7e9349eb1d9599c28ea05f763695d12b8f1ff27b0 - checksums.txt: fe62743ace57e986333b62630bb8ac7295ef869b376317adbda7296a4b67c661 + bundle-info.yaml: 049c1a9e1be6448475ed33d533ab02eaa086bb2cacf809ce37c3a153ffff2ec1 + checksums.txt: e9c25c9298bf9018321fa78075c8940e01bd5dd48babeec108da0ecbb265bb7e deploy.sh: e149421402115939cf19fcde8aabd5386462e32d4c422b8bea3cbef73a9633e9 - recipe.yaml: 1c68a28cff255ff927ffb43aa0f016f768980cad3d87020dc8914eea7b85d8f6 + recipe.yaml: 171a375ac115b924e7603c26630d53c66087a5b0b7d12433a8f1977cb400babf h200-eks-training-kubeflow: 001-aws-ebs-csi-driver/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-aws-ebs-csi-driver/install.sh: 4b3958a35a18427b6ccbefa30abdad829b99178677311ac444eff3e34c6479c6 @@ -3300,7 +3300,7 @@ h200-eks-training-kubeflow: 010-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 011-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 011-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 011-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 011-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 012-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -3324,12 +3324,12 @@ h200-eks-training-kubeflow: 016-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 016-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 016-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: f759b48a96d5d551eef4943dea02a35745980642d599167e354cf4a2e9fade24 + README.md: 7349070d39f7dca11e0a43160aba84cf78cba1661b3a5fcd04f6d2692ceaa144 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 7da9c570b61105e630eb03ef7b7950d432c04dcdfa14d3f5f4b03d490fead274 - checksums.txt: 21c88c5219c1b5958231732984aef152305ceb7256781d67cae0dbd5651d5c3b + bundle-info.yaml: 7583f86ac3a6c1d74f5e6b5e6549f086e9ade15903976e050e7b0671481c7f75 + checksums.txt: 798f03f04f967036283bdb8103d1c5fc99f6f0da62043d7121629fc7de0f8c6c deploy.sh: 5b2acd33c456f23e8d1f4d574f94b9ba2bce52147876f165a54e3395e55de09b - recipe.yaml: a306d46ce21d404b811e5c4d896e9b08cb066b939b323f32b4dcd31ab1408b1e + recipe.yaml: 401a815e2e83398ba6c4a5f063c3156d14546b4ca67ca0f93aa02791fc25bef5 h200-k0s-ubuntu-training: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -3361,7 +3361,7 @@ h200-k0s-ubuntu-training: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -3376,12 +3376,12 @@ h200-k0s-ubuntu-training: 011-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 011-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 011-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 108a41246f6812282fff9686c82a9dd8b5298e424d98034adbae462b0838381f + README.md: 04e0a15fed39812db2b8ca1b2548ee64f989f1077ee059c8c4d53b2d50ac9109 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: e1e276ddcf93d161ac458f60ccfd053898a0c447345a8eb4601d3455cb0777b7 - checksums.txt: a454a3eb0889c1841f8e4f96646542123d9ecdf09e735fe8f9aa242d91bcbd6d + bundle-info.yaml: 5cb958115b14342304a369c061748c620bf5e2bd83e0330d112c95fb08c56353 + checksums.txt: d3b145cfac91c7398c1887fb2aed2e9bce0f35d7caa8beb80301c6929e8d5020 deploy.sh: ea70804cf5d8c0bb716ccd59ea4a31a1037672453aa11e2e2bfbd20daf55d901 - recipe.yaml: a832789daf7f642c3859e7b4250c48775b4909ad6ebab1e28fe35da6b039d7fd + recipe.yaml: b71e0e2fad805c78fb47968f2af619f6e3cb2569414455e351735f5c0845970d l40-any: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -3413,7 +3413,7 @@ l40-any: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -3428,12 +3428,12 @@ l40-any: 011-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 011-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 011-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: e37d0a2de4211cdab60ee38ed8238d108299b48a24b3486597aa513d3e7dd6a0 + README.md: 0aa6c908d0faaf13e474ede80a44fecf82e94656a0be162036e3f9327bc695f1 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 8bf89ddb5d08fa480102fd5b94cfc503136b6e32dc9112670d34e88be35e512b - checksums.txt: 73064a3827687cadf478e01f205199ab2cebec4b6ba2a87639bafcfea5f165ac + bundle-info.yaml: d90a86a7abe0de1009e4383f07c7a9b973a895d228a34eb093595a8cd5ecb7c3 + checksums.txt: efd7704d6abe1d47a385e629d2b4192431474ad31112d46c1a95c55e7a6ce68a deploy.sh: ea70804cf5d8c0bb716ccd59ea4a31a1037672453aa11e2e2bfbd20daf55d901 - recipe.yaml: c345318265e9156cb210d47e6481ce4d106c458072658fcb215b7e1a8af3775a + recipe.yaml: f12c60510c27643926e5d358abe6041f0f4fd470e4ba82b242664f5ecb3a2371 l40s-any: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -3465,7 +3465,7 @@ l40s-any: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -3480,12 +3480,12 @@ l40s-any: 011-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 011-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 011-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 845cef314022dcb5eeca65b550104b817046d099937cfadcf711cd300485e0cb + README.md: e659c835f2788783abe987944d70fb62989207711bfecf3fe9e1003742046cb5 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 5efaf3183b4bba279b84f3d5100d73d558eade1efb9d0881f7a591f8cb1ed11e - checksums.txt: c5c6510bb8087ccfbb89061a0010095fd8f3e444544cada5374ff3bdbb5a58a3 + bundle-info.yaml: 5318f9fc708116c67b78b29e35a4b3bacfe4a191614723a8c8c1eda5433f4718 + checksums.txt: 550e3dfd835edefcc0f39ec4cba0ee041188a22c91bf4e39c01bb2298e087faf deploy.sh: ea70804cf5d8c0bb716ccd59ea4a31a1037672453aa11e2e2bfbd20daf55d901 - recipe.yaml: eb12a1fc5f7544b4d1ef4a6fe3519bcc40b86d89f5ab45a8d3b5b250e772cbb3 + recipe.yaml: bad37c2c8f36749dde758b89a532f87094e63985e84bf6b81ae2e26beb4dbf35 l40s-oke-inference: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -3536,7 +3536,7 @@ l40s-oke-inference: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -3551,12 +3551,12 @@ l40s-oke-inference: 015-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 015-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 015-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 1d8048fb45f088cce8cc0a6c19fdecdb9a6c7ae544b2710a80e19899d4c3db00 + README.md: 8faf2df2773bf7f587e73a2adf3bd7352e685f9eac9cde348472a82cb603787e UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: b8aa88d25e096ab8e45f06784d774d41f409528a2da6ce49a4302d321715b6a6 - checksums.txt: 8d73a9fb56f2641c36011e5bb1f8a5b211cf0d5a171625192a466aa31118247b + bundle-info.yaml: 06358efc77cf9c82e749b2531ab3f7e84531ba492f77a4c6029061b197a9c51f + checksums.txt: c2e0b9b79d097748597f21c10b72b710de76b08d58f8f2c385450be5c2aa9e09 deploy.sh: f5e448117266a5341c361f7468d2b4b0460be002aeb1dbe550a89e24a4689240 - recipe.yaml: 71537d8ac7d90713062ea4fa3eede3a657948522970e42ba8fc957807c4793b9 + recipe.yaml: 5735e99ad0222ad9efcba7a2b7938341a2555b2621aa564fa109bdc52558f666 l40s-oke-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -3597,7 +3597,7 @@ l40s-oke-training-kubeflow: 009-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 010-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 010-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 010-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 010-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 010-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 011-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -3621,12 +3621,12 @@ l40s-oke-training-kubeflow: 015-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 015-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 015-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: c28b433be87a8cdb602607be8189d565ba7b30f21848ccf2d6c59514499f5869 + README.md: caddba10d13784c4ccdd8b1b65cb337fa8db64366d855cf46297f78b7e08414e UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: a66fb62309da40de238b26ca0fd93c63fa29ad7b2ab7aafd715cf3c14d32ccd4 - checksums.txt: 75f1eb31fe54571404147cb4f096ff87d174f68711d5c29743ad4dd124457993 + bundle-info.yaml: 80088c08878da2b50b075b555ff8d3d7761ee2ac7dbf789f50428b06e59974d7 + checksums.txt: 8d2ac29572ba519e125a7fbda7a300f4403a460d0012b970c08e50badcfdc651 deploy.sh: 83fa4613633138d6b344997098cc0b2f77082f6fc1ba1cca6cef729b1a316cd3 - recipe.yaml: 452940cced0ab1323605544acbedd1e6b79cc5e388aeb3c57334d8fe5ca49db5 + recipe.yaml: d45b4710f492952261acc68449cdefb2b90c037e63311f9a05a29ae370e3552d monitoring-hpa: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -3658,7 +3658,7 @@ monitoring-hpa: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -3673,12 +3673,12 @@ monitoring-hpa: 011-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 011-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 011-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 3d899242cdd95f1b3eecae98bf74d77ec53b68fc8a6e6569114e49a055444ab0 + README.md: 3df8c21aebe85d49a3bf75665921ae5602d322146f9f9604e6eabd5ee9d50667 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: a20831b311ca30312daed6109af9023f25ddbd565139a531c4ceeab0e16d93c7 - checksums.txt: fdf572c819d4b79490af4fd28f3766f63e4d282940dc3797db53eba2e4ec9ee4 + bundle-info.yaml: 93b35a62be30baba0fe5a259ee019fb1c7a5433dc3b890cf7bb994f184d7bf83 + checksums.txt: af14031f91df0dd318c377e6b6cb9d532156141c8b6b933b213ce00563b9e8db deploy.sh: ea70804cf5d8c0bb716ccd59ea4a31a1037672453aa11e2e2bfbd20daf55d901 - recipe.yaml: 24ab49f88b9ed8b9cb3b1efdf9e9b609a1e6cbfbaa83686dbc5a29fb0f59a1dc + recipe.yaml: a43dfa467a128eb2bc82812c1804b20c254298f20d314dcf31f0e516ad37ea0f ocp-inference-nim: 001-nfd-ocp-olm/Chart.yaml: af13850294d68e9730e11e9b15c329a1935088f4e07c0ffb65a6d8a5915b78e0 001-nfd-ocp-olm/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 @@ -3869,7 +3869,7 @@ rtx-pro-6000-any: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -3884,12 +3884,12 @@ rtx-pro-6000-any: 011-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 011-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 011-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 34f29655c21d9afcc0522ad8e0fa0ae3dc6fa4d6437f71bdb9b8bdde8411b2bb + README.md: e541fb722cc178fb2105707d47769b08c7dd2a03828d2703e87f2d49520e4d8b UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: eefab36fd4795211a800193574a9257548c39c449b56050f1e7cecbb88c88b57 - checksums.txt: 819541252dbbc3ff0214e2ec32f9011e502d7b35aab28fc2f575db569530c2ec + bundle-info.yaml: 0e7c83736f635cb704dee1217a73226e51bfee5bf0b2932fa1482c8ee26c3651 + checksums.txt: baf184358ad8cd1987965b8a9d6a4792c05ca909d28bc8969d73425dd58c79b1 deploy.sh: ea70804cf5d8c0bb716ccd59ea4a31a1037672453aa11e2e2bfbd20daf55d901 - recipe.yaml: 32b380c2cd938bb330972b086538fbb275b350af83d0ca97fe5813a4f2db6dbd + recipe.yaml: 6fa21e807bc7f52fd2e866a5c74ac6171f0d486116b727e92e322361ba9dc9c5 rtx-pro-6000-eks-ubuntu-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -3957,7 +3957,7 @@ rtx-pro-6000-eks-ubuntu-inference-dynamo: 015-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 016-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 016-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 016-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 016-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 017-dynamo-platform/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-dynamo-platform/install.sh: 26f4a6ece285df70c933829cf3fc476fd3b61b711f858d86dd77f5abb22bee24 @@ -3976,12 +3976,12 @@ rtx-pro-6000-eks-ubuntu-inference-dynamo: 020-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 020-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 020-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 4bfdda900cf0d4b4c257a275350390c565a2c25cb57884c5fc72a3ab6d5556c2 + README.md: c8fcae5802cfba615892cf865fc2a4118d4298ca3ceac4ca104ea929fa629dc5 UPGRADING.md: d27ec18c5dbe463bc50dfdde771821d0a717e350be36a89f87297ada543ba81c - bundle-info.yaml: 6f400007a5f7ee13ac7e76b43954dd1ad8110b46b96d3fcf2fccf70b272d435a - checksums.txt: b78183464390709453062df610bd30d1c28ce314103e9dc34a26a3222e158821 + bundle-info.yaml: e68f177d9297a08fad1d859b53be88f5027a47276245d33d1364cef7794fa252 + checksums.txt: 100892b65916fd0a219092138a38cfc8572062b2050678206b7e1b9c0cdfc9f7 deploy.sh: 7a305353d31349834943e912d9c671f1e44a3b9ec914d8862017d7e56dee9a96 - recipe.yaml: 4db38877fde150873df88175456a635e4838c46139cffc06a1ea6c91dd8afd52 + recipe.yaml: 6b7ae881b1abd3f0a49e761885fd337db16f843416079aa99286423ab1d17ccf rtx-pro-6000-eks-ubuntu-inference-nim: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -4049,7 +4049,7 @@ rtx-pro-6000-eks-ubuntu-inference-nim: 015-k8s-nim-operator/values.yaml: 09dc1eb39d26de0971d5bef591a61a7faec57c01f09388407951b8b4733fcc53 016-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 016-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 016-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 016-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 017-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 017-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -4064,12 +4064,12 @@ rtx-pro-6000-eks-ubuntu-inference-nim: 019-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 019-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 019-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 661463f3a9658588dddef8934f676c7bd67f5cd785be1e5ae643d296924e8b79 + README.md: 8485f08968d7217d1ae1ba7b3ea11609a022f03ed19ab61d1a052eb5000dfe1d UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 6204dcb7f80da4d3a4527810e266489ac872aa415044cddcb824e30ca8425a4d - checksums.txt: fc08342e3dcbd31e8cf84aa563dd3efbc1b4baf49403c0917092cd9afc99603f + bundle-info.yaml: 5415e05e96a9e21ddbd7a21d60a6c0c39ebebc3ffa073ec208bb3fcd45d16088 + checksums.txt: d428596d5c83f9c9e7953fbbcebae50cf2891a906287705b71795eeb8f3d5815 deploy.sh: 038181d6586cb77d4ab6094a7ddd94e9db4b9c73160da7aa5f13d7389f5166e0 - recipe.yaml: 21c7bf1e9aab60439f6dc9d84178045fc74187d858eec18bc82be7cbaf5a5855 + recipe.yaml: a5071086b6bb0c4beb3a3a1afce78e4a0502bf89509f775cd1fe8a038c097eb3 rtx-pro-6000-eks-ubuntu-training-kubeflow: 001-aws-ebs-csi-driver/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-aws-ebs-csi-driver/install.sh: 4b3958a35a18427b6ccbefa30abdad829b99178677311ac444eff3e34c6479c6 @@ -4114,7 +4114,7 @@ rtx-pro-6000-eks-ubuntu-training-kubeflow: 010-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 011-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 011-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 011-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 011-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 012-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -4138,12 +4138,12 @@ rtx-pro-6000-eks-ubuntu-training-kubeflow: 016-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 016-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 016-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: a0984a093f9000cad08c5ecbbd7088ecd4b54ab3fb35f401d0e2ca531ed2edfc + README.md: 9ffa96d03eeb195328482b7b828ea3cfb2a6ba9be55fbccc6eeb976c69877005 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: b049397b787a94d946349995bb2f1002fefd2552e479bef7ec019b5a2eca2be6 - checksums.txt: 6843362c2aac4e41c84b499d141c691a5d0e6fba6b3e31f103be97b4a33be15d + bundle-info.yaml: 5f9bf287a516d6c03f100e1bd193eda98f3f577dd7ebc14b0a34caa9b70ffa9b + checksums.txt: f5981ee48881ec5425cd7218a25ffb82f29330402fffe34a37dcb128c11e1b24 deploy.sh: 5b2acd33c456f23e8d1f4d574f94b9ba2bce52147876f165a54e3395e55de09b - recipe.yaml: 20afdda5c4355624e51050d78973b4f016e83cb9bce0b4bbf25e83c1e5f2514e + recipe.yaml: c56085ce2e6e66436c91d7010878b3d68402b5fc2a040c88eb0da5d84f57ccd9 rtx-pro-6000-lke-ubuntu-inference: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -4194,7 +4194,7 @@ rtx-pro-6000-lke-ubuntu-inference: 011-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 012-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 012-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 012-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 012-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 012-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 013-nvidia-dra-driver-gpu/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 013-nvidia-dra-driver-gpu/install.sh: 6d3aa21c099c4d498707247ec21fb53f18a82dcef3408e0f977d3e0be4c36331 @@ -4209,12 +4209,12 @@ rtx-pro-6000-lke-ubuntu-inference: 015-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 015-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 015-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 2bf65a4c61206273ba292c2cbaea904102487ef248887eeba67114d9a13cdca3 + README.md: 530b272b7db0414e168d24eb55a7e3667899936585ebbe82a55b6e12f71352d9 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: f2b647f4d5a54286cb6a4fb7860e51e49231535ac15b6536dbd13d262f2aa0d1 - checksums.txt: c6ba60cd0d11227022dfcfaea0d4c7716a71c4388f9b2cafa0fc2af85de257cb + bundle-info.yaml: a6805e4c8dcc612db5b935257425daf67749901aa740652227bdec8500e0e7a9 + checksums.txt: 220420e0f350c02759e24b514802b4e8340ab2f82ca807b9c6aac494b73aad5d deploy.sh: f5e448117266a5341c361f7468d2b4b0460be002aeb1dbe550a89e24a4689240 - recipe.yaml: 2637f0fd131e88d5adafa415d7de0be4e9bfdd38a17288f880dd40f3d616eedf + recipe.yaml: 3f6deb258ea80e916935c8bc95e6a4f6d6e55fa072ffcdad79c6772c272db854 rtx-pro-6000-lke-ubuntu-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -4246,7 +4246,7 @@ rtx-pro-6000-lke-ubuntu-training-kubeflow: 007-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 008-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 008-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 008-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 008-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 008-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 009-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 009-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -4270,12 +4270,12 @@ rtx-pro-6000-lke-ubuntu-training-kubeflow: 013-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 013-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 013-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 7c35d1cc30c8e737e00bb5316bd85226e888834ba942cf1acec838e7cd435000 + README.md: 098be85aa6a03bcc87efb02c3416eb8e2cf67f076c34ab3ad23f16a39d933235 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 3b51439df6f782b0664fb14b73c7decb36cd2d943ff11a39478eb26d9348723a - checksums.txt: 8e1207dc77a0b1cc087633248bd58507ee1e8e7944cf3356fa709d13c354fca5 + bundle-info.yaml: e43879c485b5aaa3a363c2819ed45fc288ae9fe4f9c4b536363cee7e20e608dc + checksums.txt: 916027065b1bf91fc04f72b055531714fbc14776f0ea62ddd6a5aeeb9a5cf1bd deploy.sh: 8ebf4bd801a6d8fd6cba8979dc354e9aeeb8d5cfccbee9e6e7262417b175c6f4 - recipe.yaml: 953b93749485bc38a22acf5d0ac2b0e458df9d02d9e087c3e095403df7f8e84a + recipe.yaml: f9a19680179c8e4ee175eb0c5a5d3ac2fc59258cdbd47796589886986fa11ae7 vr200-rke2-ubuntu-inference-dynamo: 001-agentgateway-crds/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-agentgateway-crds/install.sh: f0f864c4eb1f1d647af123953d5df5aa1fa03226e1f8c5feb724ea42d304eb3f @@ -4341,7 +4341,7 @@ vr200-rke2-ubuntu-inference-dynamo: 014-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 015-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 015-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 015-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 015-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 015-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 016-dynamo-platform/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 016-dynamo-platform/install.sh: 26f4a6ece285df70c933829cf3fc476fd3b61b711f858d86dd77f5abb22bee24 @@ -4360,12 +4360,12 @@ vr200-rke2-ubuntu-inference-dynamo: 019-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 019-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 019-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: b0d4dc1341565474394f7c338e1187f97aaa84f2506642d2c91a212f57ba1669 + README.md: 2580de414924ad6ceff29d99cbcf2c5a86021331cd63aa89d061cd92cf99b460 UPGRADING.md: d27ec18c5dbe463bc50dfdde771821d0a717e350be36a89f87297ada543ba81c - bundle-info.yaml: 3614ecc79f449848f257e036fb15a0b8fb7cf24fcad50d0079468a98cc92fda3 - checksums.txt: e89cc487af73cecd7dee840f690c6cc66a1c41f27f337eb4eb00506336fd09d5 + bundle-info.yaml: 45de6b90caf5e022d2e4db2f70f60ce31bc438c1f0f78d093eef5becbddad455 + checksums.txt: 7d5d06d1f62dde2b2d222f76cc0a7e556730b19db71868f89e73663131f8c1a2 deploy.sh: 62b3ab91044223177c74d3aee7241f4aeae64e6bdb31481f7da642dbf4556e9a - recipe.yaml: e3ca2966624bc02a472b86a93d10a8786a869e74fb461420ebf4d8fc0b208f87 + recipe.yaml: 283f2d6617538a111b4283b5d38962ed664124951486b9e244f9be874db1bb4b vr200-rke2-ubuntu-training-kubeflow: 001-cert-manager/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 001-cert-manager/install.sh: d8043b8845f8225dc46f54e05a3a86362e30487775b59ac74f47be104e8555bd @@ -4407,7 +4407,7 @@ vr200-rke2-ubuntu-training-kubeflow: 009-k8s-ephemeral-storage-metrics/values.yaml: bd965e10e0f6eca07d732ea00d66e8327c176acfdc52d998809f7d4d53e056e8 010-kai-scheduler/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 010-kai-scheduler/install.sh: 529a6fd19ca71cbf0d2f5bcf40ce817db93713c5c0183e59d690bff9745f95cc - 010-kai-scheduler/upstream.env: 28796b9c560ab50439fa444585d161dfdb838c82420680a85a0e6eeef3fb7af0 + 010-kai-scheduler/upstream.env: 1f0e3ae5bad0a40cd7d4c81df3000341d4c0c815ae02abf860f1fed27ffe2c79 010-kai-scheduler/values.yaml: 478f75baf393a9f6c9425b543f8ea2b3103b090e75dea49284805e0ddd625265 011-kubeflow-trainer/cluster-values.yaml: 49f560d440b0b58c4ec35c7f72fc187f23b94a69f5f7135482fa7070310bae26 011-kubeflow-trainer/install.sh: c70bb2b465bb7b53ba6257686458e82128ad52d73a9fa231769cc32d3086d51b @@ -4431,9 +4431,9 @@ vr200-rke2-ubuntu-training-kubeflow: 015-prometheus-adapter/install.sh: 688ee4274fe06c001af6835d7965b5da33ce3fbeb724263622737d0bb88249e3 015-prometheus-adapter/upstream.env: 9ab918b32522baca13cd37bad7f420a206a19bb763b81041e174fffffe3da724 015-prometheus-adapter/values.yaml: 95231d7a46d650f96f844ca3734614271152a41f1230022c9d79960e44647c00 - README.md: 80e547edb47741f31f7b21d02cbf9b0fa9a17a99b2a7320cbdff82d856d1cb81 + README.md: dc562ed7e4868f8f49d9206641c7d47f89647c62cd148799f9e96e1d57241f30 UPGRADING.md: ac50a3b91fe4d02988ef696661f8ac7d5e6854e49419d573361ad4f2b280c327 - bundle-info.yaml: 5bfe00acd931aef4736d88e05805e651f6bbb6d1afa830294329f81d2a74c7f5 - checksums.txt: 5ca2e27c469f913d24310d8fcfeda43dfa41610d63be12718d6c4a105dae9db6 + bundle-info.yaml: 9769fe648e7ea4c6eef2116df62a906c46745a49fba222de69f7feb23e8ae914 + checksums.txt: ffeafc9fcf20cf6b5dfd921a8a0643328ef889b7bbcaad32d7be983ba2729886 deploy.sh: 2b0cd173c38bb27ee4cdb7d6c4d1d94d523b56fed94d6889cacd342b0b5a0dfd - recipe.yaml: eae45aaf8edf5ea05bc9e583440d75ffcdf378166ca86e5e469cd3e572b00e07 + recipe.yaml: cdc782b615b12a5870cb70c51383644fc36fe97873c5cb4644a667ba719ccdc4 diff --git a/pkg/recipe/testdata/catalog_parity_golden.yaml b/pkg/recipe/testdata/catalog_parity_golden.yaml index 1c4cd53499..45e442ad36 100644 --- a/pkg/recipe/testdata/catalog_parity_golden.yaml +++ b/pkg/recipe/testdata/catalog_parity_golden.yaml @@ -3,62 +3,62 @@ # # One entry per leaf overlay: sha256 of its deterministically-marshalled # resolved recipe. A moved digest means that recipe's resolved bytes changed. -a100-aks-ubuntu-training-kubeflow: 9ebc4336754eaab53ac270b8867ae846492d7eabf3b6856f0eb5ae89b76caf8c -a100-any: ebc8c349649ec02ac626d5f363c3a7c902cee426fcae69fdb56dfcabbf8945f5 -a100-eks-ubuntu-training-kubeflow: d81a9379084758fd939529f729a6cfd97297221eaff7d2cc9cd33ed6bd7d2308 -a100-gke-cos-training-kubeflow: 913d51ff9e7891d377c905100a0001ec8ef0cf8535e0792f8c715f1b2d1dcbfa -a100-oke-ubuntu-training-kubeflow: 1a142ec81fe950cb8b9ecd58e375363184b103dbb803ba43aaad3ef4c947232f -aks-ubuntu: 50653a9d3874c6a7d3b4b7c9ec2b3cc60de0982bbbb1ca7c48602553d3befc0c -b200-any: 6874f651fff74a5df080ca7e4c54ec2ef9823ff0c3cf72d953e64e6ef98a4af9 -b200-gke-cos-inference-dynamo: 0b9aff411203fafdba2beb47a4f8d79ffc42e6ec68c4e3053a74efee4d596ee9 -b200-gke-cos-training-kubeflow: d234168cd9b245c4983e750dee6ed26f67025ca376b3db20ef80b8b6f6a47d45 -bcm-inference: 6f136582c3989249580f0d0fd4200df1dff167719dcc437accfab08097ab23a0 -eks-ubuntu: bc8d2ac072df16e990ecf76ceb60bfd0be8dc854867d9b2fbd9c5daf05c215f8 -gb200-any: f886178cf74ec415ec2e95e9a32f2b8c41416684a62ef5cbe277288c14699c1f -gb200-eks-ubuntu-inference-dynamo: 7c205fbad4c98c153b1b2b8784a975959787e19aa3ce616fdccb0bec97ce4b80 -gb200-eks-ubuntu-training-kubeflow: b1590df9addcc3ff3386e0a2d25e658396731f67b320573008d3426ead84c2a4 -gb200-eks-ubuntu-training-slurm: 7e9b4e16b61e2fb527b057b6ffcca8a30528138e06c9e7bfcc6b364076881c4f -gb200-gke-cos-inference-dynamo: 20400798cbb2c9e65265a88e9e72a898f8b132fc044b92e0c915f2169e89512a -gb200-gke-cos-training-kubeflow: 77064b09640222b09ea169f2c7064797224c2121d2a184c90796651613305112 -gb200-gke-cos-training-slurm: 413067bfaba04f77a53f65b9fe892e0942ce3977f49ab236bbe2035f6a683ff9 -gb200-oke-ubuntu-inference-dynamo: 4166375b2e48875a7ee2a4bf7c6b45762367d3d5ee2a4d326a97c44533a76ffa -gb200-oke-ubuntu-training-kubeflow: ff62cde41872e5fb9c52c97d2094a7952e5d514970a753e91b815fa66f0c90a6 -gb300-any: 96aa04360e1f10f8b42e5bd1f918d558d41339cb002bf515ef6dac53f3c9bd5f -gb300-eks-ubuntu-inference-dynamo: 2b3d513ba6f063648b7bcf3e38ac3e9c236be8328f8cdbb5599cc668c3ab66a0 -gb300-eks-ubuntu-training-kubeflow: 8874fdf7b8060fca11f7412e2c7090d0869c068ad5d352be7b4c7957f52ab311 -gb300-eks-ubuntu-training-slurm: 3b2001ec27233f382d518ebc2fc091186b74eea8cecc5d6898d045b9d0dd158e -gb300-generic-ubuntu-training: 8cd1c26e2d7b9d7f0605695fbb32d98f5204e282b7b0e52473f40b9761287bdf -h100-aks-ubuntu-inference-dynamo: 54ad5bcf3ecf22ade1720091d8ab3a260ecb7b0784824417c1d77683693e6d5f -h100-aks-ubuntu-training-kubeflow: 9936cf1a5dce954f41c2076ba1bcaa1e029e19bee4d0660e07fc39e08b682a15 -h100-aks-ubuntu-training-slurm: d25674a9b57cd110da31466c16311f22147a6ce3dbdeb61531add084915d5949 -h100-any: 902ee0497cc4358441c42f533f01438be066b318def504eaf30859fd8f9b90d2 -h100-bcm-ubuntu-training-kubeflow: 7e850295309d0dfb6a65b990a52b69fd3a892a352b846a909e956b41e2485c18 -h100-eks-ubuntu-inference-dynamo: b5c1edc0859c57fcbbf8a429312f1ccc225793c28774405b6692550aaa81b50e -h100-eks-ubuntu-inference-nim: eed32e85aa44bd0734aefaf7214866db7a80d28711d65bb423d47ea4c1113862 -h100-eks-ubuntu-training-kubeflow: 03990c0bf9544f1914f55fdb57a53b4dd2214fa922244994b8cfce538f3d143a -h100-eks-ubuntu-training-slurm: e528a54de4b0f9a37406bbe3aa4725ad0fd38a6d2b55ac65b3bf4eebaf0e13d2 -h100-gke-cos-inference-dynamo: 3392baf8b9bcec9eb7d3cfe5d316dd9d32b1f4277e700c29c1b67c65efb8eb9d -h100-gke-cos-training-kubeflow: 16c3fe5d2f954caadba58a3d319acfd2db229ed4f0474d78ac30157483e2c5e0 -h100-gke-cos-training-slurm: cf1f6d42132eb1bba7f28a4bef4304328e9bfd2593e7bd2dd78b98c0c83b21ff -h100-kind-inference-dynamo: 5552082356c8339d3c54ee6e275659e690913c138448dd1f5e1eb4a6e9703a5d -h100-kind-training-kubeflow: 52bc7adcf5b36ec774eb1d5212f63eea9a4253130ce6d1b6d80199d123115d01 -h100-kind-training-slurm: 7a6acbf833aee54895ec9ea29c18faa90ac9f401f100800a333eb154f8e38319 -h200-any: c560a926b1997210654edee1d2d299f59ca7bd58d7ae11679b4649ea63b095dd -h200-eks-inference: e8108add208b99f58fb9c9f49da13a9a149509075ec730db580b52201e67b1a1 -h200-eks-training-kubeflow: 4beaaf1f420c840b42d50b29595013f0cf8674ff4963ff75f9cdbe96805cd66c -h200-k0s-ubuntu-training: e71198e2a39b4e1bb6d5edc9df82c3b9635d2a9816817ed50c789b0b75b264e3 -l40-any: a52c121922c1da1b6314f334126c9aa98ae3a43afa1c86d4efd6816894eee4ab -l40s-any: 3afebb0f97c812cfcbcf2f5073b56e7003112eeccf730549444ebaaa47017337 -l40s-oke-inference: 5f01fc946c4c861853a407caa7d0216089006b9ee0b0e1d53b8eca49c2446317 -l40s-oke-training-kubeflow: 828ac27512883fc909892691da8d506340665bbf9b353a5466f78215e6b20eee -monitoring-hpa: 1e9eebd78651a0a815a5dbc606cb3a0a01135bb70b4133c3f97335761caac42b -ocp-inference-nim: 5acfe4d5eda4da2c5b37a40e1893404768e515dd3501203b859895b9ada50a1f -ocp-training: dc0baac0c2ae027bd07bb36e47fb24f88a95348556fdb1ba5b0c5bc403be09bc -rtx-pro-6000-any: 8466e67705e446d563ababe788f37fb1929d99995554b30a3d6a4ba85bc800b6 -rtx-pro-6000-eks-ubuntu-inference-dynamo: 7c835915dbc6e95a3e377629b62bc0a8777700d7e5a75d6226deb740d7d17ed2 -rtx-pro-6000-eks-ubuntu-inference-nim: e282ad59490bdb18fd816d785dad397a18d06e8cf9f31240c897d65229231828 -rtx-pro-6000-eks-ubuntu-training-kubeflow: 69fe59ea60355f2c00680d44fb2ce43163f8d10825abf8c06eb40b608446e67f -rtx-pro-6000-lke-ubuntu-inference: 4a60db7496779933e8bd676477cfb5d81e40734db25c1442031b2c6ebf58d2d6 -rtx-pro-6000-lke-ubuntu-training-kubeflow: d978ceb4c675586a39750392efc8b83dd1c19011580a8e0ab4ecc89aa1f6b748 -vr200-rke2-ubuntu-inference-dynamo: 8b6a2a9d5c231e058d95bc3cd6edd8707dec2def5ef305e61c935573770ffbb5 -vr200-rke2-ubuntu-training-kubeflow: 929be4288ab9c81f2c4a0d7ed5eb569892b74df8a81189874cd5addf1513b73b +a100-aks-ubuntu-training-kubeflow: 4b13821bce7ac0c3adbfa9357b496995611317b976d262ad37f4c40e14c32ccc +a100-any: cd048f835e3c69ec7bfb433488c7cb07a796c30e42a65e5e274333185287f012 +a100-eks-ubuntu-training-kubeflow: 5f7b75fbb3703011436dd1302fe3590c32e6b2e9c71a45a423df9d4f17bef135 +a100-gke-cos-training-kubeflow: a5a0fcb578e1eb3e1a580618cc3464b7167b7460edf90b2345a5edbdd93e6295 +a100-oke-ubuntu-training-kubeflow: b552b789fce48c8243ba1ceaf7e6751d89504d2e67dce473fe283aaa8883af8b +aks-ubuntu: cf45088a5c85f17aee5a68b1474e01204da9688369e767d17371764752afeb41 +b200-any: f7fe8044441bf60e3ec53d1cd185f76e06e4e39be8551944fc2a816057ecbf6e +b200-gke-cos-inference-dynamo: c211b3836bf28237a1ea85c2f669aeab4966269100890a5b03f4e2ac0f679167 +b200-gke-cos-training-kubeflow: 28ca792b2814a436a28a93e05726d3076602dddf644e959f809913e90e5f28ae +bcm-inference: b4a0a7f22fa3abc07331de3600cd073436d0edc52481e6d9e16c7b508fa88648 +eks-ubuntu: 43c2b5575a44124c9ba9bb7547f9ea337385e44d27994aaae769955fd121fae4 +gb200-any: 2b65fb20ffada538c5c1c5ba2c409e5e52aabfa8a4742d6005eeaca9f3449006 +gb200-eks-ubuntu-inference-dynamo: 53b58b7a5b512a358d86cf209b54442ded8ff6f8a68b8f7c22dc495e5f779ddb +gb200-eks-ubuntu-training-kubeflow: 92366827e6a3092abaf77181a92884603ff75791cf5b3009cded8ac114b8825c +gb200-eks-ubuntu-training-slurm: 301a5f538fb3266838b6a4058b7f64beb68c48d7b98ac79057c4da0d88055fdd +gb200-gke-cos-inference-dynamo: 75ab66fa1050a0fe3a810629baa73b4cfabfd79043505f476d502b44f66a4b8c +gb200-gke-cos-training-kubeflow: b4aa83c3059611e68387441dff484117d200decdbb3c75217403730d295d054b +gb200-gke-cos-training-slurm: c55a143e7cc0688fb8c79d6541ef9cd22bb57e33dbfb41a2eed35bcf558ee3c0 +gb200-oke-ubuntu-inference-dynamo: eb4330ede8f25cb57759f1c705bf65efa60fbdcda9b4e591ff67740b7134aeb1 +gb200-oke-ubuntu-training-kubeflow: 010226fbdcca06606fef52ee1ca939c496c0812a7728ad6b5639354af41db295 +gb300-any: 62570a884e39d0007e76c47da16c76c4d43880cb5b245648df4d9ef389a02dd9 +gb300-eks-ubuntu-inference-dynamo: 84ab0d30664ec014eb1f3441c81ecffc770ebb467afcdd4ad50899fff50bd55f +gb300-eks-ubuntu-training-kubeflow: 266b976a92e644aed30914f5e05d418c76b4a1ead6454fe7a8f3ed8acb0b3de1 +gb300-eks-ubuntu-training-slurm: 5f32beb9d4e149db0edc3f88836130eb36409838288427dc07f0f4e68fa380e0 +gb300-generic-ubuntu-training: 60551c1f5a7068cf37f5ac8d6be46d7206da893bbb8293351b66d6288a05906e +h100-aks-ubuntu-inference-dynamo: 52f6daec2ab652f6b95b2670fe717db319a1d5b4e3c88046477c7b851aabd9be +h100-aks-ubuntu-training-kubeflow: 46b3e61c77213e4c5ac27c84b418e0a387c5bae0658baf35344a593da1941c57 +h100-aks-ubuntu-training-slurm: 0b0e91db817197b1cfd9b034806aaac002025ab7ce219ef5770d8b6d11410c85 +h100-any: 0cc82f9dc2d079f8999329904d3210dd2ecd17c86241bc6e0ad4016848cf4dd5 +h100-bcm-ubuntu-training-kubeflow: ab35b535ccf393aa10af172ae1aa076edb0fb0c3ed331e2a486573ce50635fcc +h100-eks-ubuntu-inference-dynamo: b50d149b99726980f615c8ee2977d24aaaf539c173b8200f110275c0a20ad587 +h100-eks-ubuntu-inference-nim: 28d3a40cbb9515b372f0e27dead0755f6fee714ea9af79ce671493bed1c3045b +h100-eks-ubuntu-training-kubeflow: 8d2f6ff1189994179ecda90ed339e7a0026edc4ce1b54d6268b841d26026abdc +h100-eks-ubuntu-training-slurm: d489d1ba16736bb7aa342b22c915068c4c59881d694f867f0df3241607c9e7bb +h100-gke-cos-inference-dynamo: f13ddef76ddef0ccf45473da42eab386daa16829b5a155887dc1c6e2d6c730b8 +h100-gke-cos-training-kubeflow: c234cdf56fb38c84e3c2d7d4d6f11802d862c1d5c2e39c3b1fad01c175fd9887 +h100-gke-cos-training-slurm: 628d8cd2e34ff4060ad979834c482d3c683ce10c9fd67fda50dbb316bab94ad7 +h100-kind-inference-dynamo: 0d537a312be8adeb0de95001392fc42b226e4c5584c861f336df05153ffdb675 +h100-kind-training-kubeflow: 31ae7e7f131dd835df0ea587a54f25cacdb5bc83bcacae8751ab5f4ebf0dd4c3 +h100-kind-training-slurm: 73fd8052f930dc91e02251566caed52c226391b986e5675edfef868591d739b5 +h200-any: f537fd731a445442572d8b5b9097db80c2937b356450f37e60f063b9b36c23d7 +h200-eks-inference: ca7696559436ec694e1a54314ac87f63d2f9b0f43111745bad0a332c7a2c4275 +h200-eks-training-kubeflow: 9f4d5e77d78bf04b4073d0188d7028c3773381db0e4e592540caa4dce1d59682 +h200-k0s-ubuntu-training: 26b1386af2b43460327beaddc2a5b38abe3be4fbdc5aaad0017c6c52fd0c4a23 +l40-any: 28a5134ffca7a74b5cb77831e1c3ed779714cbf646797567f74701be6607b905 +l40s-any: 4e5beb63cd5523128564cc44824be2d6040ce695480dc83124f40f55707df5f7 +l40s-oke-inference: 4e2dce54e055d5ee7b769816b1295d0a242f560bbdf7e5ef5c0055369eca8a39 +l40s-oke-training-kubeflow: a6591939dbf9b7894024d26713c24c60b18089fdfce7adbb75da21826eaeb5dd +monitoring-hpa: d21983e1a9f3cc86aa30f2389af825a1e3a302b10ea3a1f4ad4768f02fafc8e6 +ocp-inference-nim: d6a8c852453bb1d857a78d674bb60b18330f6040cf91f56cb94b6e5b4be7f6f8 +ocp-training: 8a38215a2134a6e58467751fb7eff7c2faff26d8daf22eccbaa7f5a8d6d22eb8 +rtx-pro-6000-any: c7005cc6b96499cf04162481ee0fa440e922d0c0866505775811f708ff8f23f4 +rtx-pro-6000-eks-ubuntu-inference-dynamo: a89fe5a1fca6bce1afa059a4ab2f888c36811f05ecf7529bb9620e55019f7136 +rtx-pro-6000-eks-ubuntu-inference-nim: 922d202b439fc555daac16a69ba97119eabee077d9d8b554b52df46a3fb541ef +rtx-pro-6000-eks-ubuntu-training-kubeflow: a46da959bcdfffeb801282a725a8f6ddd8e7dd3ab94b5fbe64921bb5a8faa157 +rtx-pro-6000-lke-ubuntu-inference: 01e784d43161af22646f7a9d0654a6f311b6747947b839cb8b92102485a31cc8 +rtx-pro-6000-lke-ubuntu-training-kubeflow: 51d4354c8f398ab5e0408475bb4097ac13be73285f69c5f8e8263361ef2c196c +vr200-rke2-ubuntu-inference-dynamo: bc3748acb2071af809fda8bd0c8505bb40759e300a5b8b97d894415c0f3e1b5e +vr200-rke2-ubuntu-training-kubeflow: 781b7e627708c74f2a706515d046dfdd35c09e1874d2abcb0950c52211b94514 diff --git a/recipes/registry.yaml b/recipes/registry.yaml index d04b372ee8..b216c449ca 100644 --- a/recipes/registry.yaml +++ b/recipes/registry.yaml @@ -814,7 +814,7 @@ components: defaultRepository: oci://ghcr.io/kai-scheduler/kai-scheduler defaultChart: kai-scheduler # renovate: datasource=docker depName=ghcr.io/kai-scheduler/kai-scheduler/kai-scheduler - defaultVersion: v0.16.9 + defaultVersion: v0.17.2 defaultNamespace: kai-scheduler nodeScheduling: system: From ec7d3c191f6f73aa26547864cd14d2367c5400d6 Mon Sep 17 00:00:00 2001 From: Carlos Eduardo Arango Gutierrez Date: Wed, 30 Sep 2026 16:22:50 +0200 Subject: [PATCH 8/9] fix(recipes): wait for the 26.10.1 data plane, not pre-existing conditions The MariaDB Updated and Ready conditions are computed against whatever StatefulSet exists, so on a healthy HA instance both are already True before the 26.10.1 operator first reconciles it. The await step could return at once and let the revert set autoUpdateDataPlane back to false before the new operator ran, which leaves 26.10.1 keeping the old init and agent images. Replace the condition waits in the helm/helmfile and GitOps procedures, and in the component-catalog mirror, with jsonpath waits that cannot pass on the old state: the StatefulSet template carries the 26.10.1 image in the init and agent containers, every named pod reports it in its container statuses, then updatedReplicas and readyReplicas reach the replica count. The operator persists the bumped images into the MariaDB spec before rendering the StatefulSet, so the revert is safe once the template carries them. Checked on Kind (kindest/node v1.37.0) with mariadb-operator 26.6.0 to 26.10.1, replication and Galera at 3 replicas: the new waits time out before the operator moves, pass after the roll, and the old procedure reproduces the stranded data plane on a third instance. Signed-off-by: Carlos Eduardo Arango Gutierrez --- docs/user/component-catalog.md | 48 +++++-- .../components/mariadb-operator/upgrades.yaml | 126 +++++++++++++----- 2 files changed, 132 insertions(+), 42 deletions(-) diff --git a/docs/user/component-catalog.md b/docs/user/component-catalog.md index 36df0ee9aa..9504bcda28 100644 --- a/docs/user/component-catalog.md +++ b/docs/user/component-catalog.md @@ -1604,20 +1604,44 @@ CRDs first and the operator second: cascade-deletes every `MariaDB`, `User`, `Database` and `Grant` with them. 3. Upgrade `mariadb-operator` to `26.10.1` (re-run `install.sh`, `helmfile apply`, or sync the release). -4. For each HA MariaDB patched in step 1, wait for the roll to finish before - continuing. The operator applies the new init and agent images - asynchronously, and reverting the flag mid-update strands that resource on - the old data-plane version against a `26.10.1` operator: +4. For each HA MariaDB patched in step 1, wait until the `26.10.1` data plane + is running before continuing. The `Updated` and `Ready` conditions cannot + show this: the operator computes both against whatever StatefulSet exists, + so they are already `True` before `26.10.1` first reconciles the resource, + and a flag reverted at that point leaves `26.10.1` keeping the old init and + agent images. The waits below cannot pass on that old state. Substitute the + name, namespace and pod names (`-0` up to `-`), and + set `3` to the replica count: ```bash - kubectl wait mariadb -n \ - --for=condition=Updated=True --timeout=15m - kubectl wait mariadb -n \ - --for=condition=Ready=True --timeout=15m + IMG=ghcr.io/mariadb-operator/mariadb-operator:26.10.1 + # The StatefulSet renders the new data plane. + kubectl wait sts -n --timeout=10m \ + --for=jsonpath='{.spec.template.spec.initContainers[?(@.name=="init")].image}'=$IMG + kubectl wait sts -n --timeout=10m \ + --for=jsonpath='{.spec.template.spec.containers[?(@.name=="agent")].image}'=$IMG + # Every pod runs it. + kubectl wait pod -0 -1 -2 -n --timeout=15m \ + --for=jsonpath='{.status.initContainerStatuses[?(@.name=="init")].image}'=$IMG + kubectl wait pod -0 -1 -2 -n --timeout=15m \ + --for=jsonpath='{.status.containerStatuses[?(@.name=="agent")].image}'=$IMG + # The roll has finished. + kubectl wait sts -n --timeout=15m \ + --for=jsonpath='{.status.updatedReplicas}'=3 + kubectl wait sts -n --timeout=15m \ + --for=jsonpath='{.status.readyReplicas}'=3 ``` - Name each resource rather than passing `--all`. The `Updated` condition is - absent until an update is triggered, and `kubectl wait` does not return - early on an absent condition, so a blanket wait burns the full timeout on - every instance that had no roll to do. + The operator writes the new images into the `MariaDB` spec before it + renders the StatefulSet, so once the template carries them step 5 can no + longer take them back; the pod and replica waits confirm the roll itself. + A resource that names its own init or agent image, such as a mirror, keeps + that repository and takes only the `26.10.1` tag, so set `IMG` to match. + Name the pods rather than selecting them with `-l`: a label selector + resolves the pod list once, so a pod being recreated when the command + starts is never waited on, while a missing named pod fails the command and + you rerun it. The replica counts mean something only after the image waits, + because before the new template exists they already equal the replica + count for the old revision. Skip non-HA instances: they have no init or + agent container, so these waits run to their timeout. 5. Return the flag to `false` so a later operator bump does not update the data plane unattended. If the field is managed in git, set it there. diff --git a/recipes/components/mariadb-operator/upgrades.yaml b/recipes/components/mariadb-operator/upgrades.yaml index 6cc4ee5c9f..59516d2f81 100644 --- a/recipes/components/mariadb-operator/upgrades.yaml +++ b/recipes/components/mariadb-operator/upgrades.yaml @@ -97,23 +97,56 @@ transitions: reason: >- Moves the operator to 26.10.1 once the new CRD schema is Established. - - id: await-dataplane-update + - id: await-dataplane-template description: >- - For each HA MariaDB patched in the first step, wait for the roll - to finish before continuing: - `kubectl wait mariadb -n - --for=condition=Updated=True --timeout=15m`, then the same with - `--for=condition=Ready=True`. + For each HA MariaDB patched in the first step, set + IMG=ghcr.io/mariadb-operator/mariadb-operator:26.10.1 and wait + until its StatefulSet renders both data-plane containers from it: + `kubectl wait sts -n --timeout=10m + --for=jsonpath='{.spec.template.spec.initContainers[?(@.name=="init")].image}'=$IMG`, + then the same with + `--for=jsonpath='{.spec.template.spec.containers[?(@.name=="agent")].image}'=$IMG`. reason: >- - The operator applies the new init and agent images - asynchronously, so reverting the flag while a resource is still - updating strands it on the old data-plane version against a - 26.10.1 operator, which is the skew this record exists to - prevent. Name each resource rather than passing --all: the - Updated condition is absent until an update is triggered, and - kubectl wait does not return early on an absent condition, so a - blanket wait burns the full timeout on every instance that had - no roll to do. + The MariaDB Updated and Ready conditions cannot show this. The + operator computes both against whatever StatefulSet exists, so + they are already True before 26.10.1 first reconciles the + resource, and a flag reverted at that point leaves 26.10.1 + keeping the old init and agent images. The operator writes the + new images into the MariaDB spec before it renders the + StatefulSet, so once the template carries them the revert can no + longer take them back. A resource that names its own init or + agent image, such as a mirror, keeps that repository and takes + only the 26.10.1 tag, so set IMG to match. Skip non-HA instances: + they have no init or agent container, so this wait runs to its + timeout. + - id: await-dataplane-pods + description: >- + Wait until every pod runs the new data plane, naming each pod, + -0 up to -: + `kubectl wait pod -0 -1 -2 -n + --timeout=15m + --for=jsonpath='{.status.initContainerStatuses[?(@.name=="init")].image}'=$IMG`, + then the same with + `--for=jsonpath='{.status.containerStatuses[?(@.name=="agent")].image}'=$IMG`. + reason: >- + A new template only starts the roll: under the default + ReplicasFirstPrimaryLast strategy the operator deletes and + recreates the pods one at a time, replicas first. Name the pods + rather than selecting them with -l. A label selector resolves the + pod list once, when the command starts, so a pod being recreated + at that moment is never waited on; a named pod that is missing + fails the command instead, and you rerun it. + - id: await-dataplane-rollout + description: >- + Wait until the roll has finished, with N the replica count: + `kubectl wait sts -n --timeout=15m + --for=jsonpath='{.status.updatedReplicas}'=N`, then the same with + `--for=jsonpath='{.status.readyReplicas}'=N`. + reason: >- + updatedReplicas counts the pods on the StatefulSet's newest + revision, so N updated and N ready is the finished roll. Both + counts mean that only after the steps above: before the new + template exists they already equal N for the old revision. - id: revert-dataplane-autoupdate description: >- kubectl patch mariadb mariadb -n slurm --type merge -p @@ -147,23 +180,56 @@ transitions: reason: >- Moves the operator to 26.10.1 once the new CRD schema is Established. - - id: await-dataplane-update + - id: await-dataplane-template + description: >- + For each HA MariaDB patched in the first step, set + IMG=ghcr.io/mariadb-operator/mariadb-operator:26.10.1 and wait + until its StatefulSet renders both data-plane containers from it: + `kubectl wait sts -n --timeout=10m + --for=jsonpath='{.spec.template.spec.initContainers[?(@.name=="init")].image}'=$IMG`, + then the same with + `--for=jsonpath='{.spec.template.spec.containers[?(@.name=="agent")].image}'=$IMG`. + reason: >- + The MariaDB Updated and Ready conditions cannot show this. The + operator computes both against whatever StatefulSet exists, so + they are already True before 26.10.1 first reconciles the + resource, and a flag reverted at that point leaves 26.10.1 + keeping the old init and agent images. The operator writes the + new images into the MariaDB spec before it renders the + StatefulSet, so once the template carries them the revert can no + longer take them back. A resource that names its own init or + agent image, such as a mirror, keeps that repository and takes + only the 26.10.1 tag, so set IMG to match. Skip non-HA instances: + they have no init or agent container, so this wait runs to its + timeout. + - id: await-dataplane-pods + description: >- + Wait until every pod runs the new data plane, naming each pod, + -0 up to -: + `kubectl wait pod -0 -1 -2 -n + --timeout=15m + --for=jsonpath='{.status.initContainerStatuses[?(@.name=="init")].image}'=$IMG`, + then the same with + `--for=jsonpath='{.status.containerStatuses[?(@.name=="agent")].image}'=$IMG`. + reason: >- + A new template only starts the roll: under the default + ReplicasFirstPrimaryLast strategy the operator deletes and + recreates the pods one at a time, replicas first. Name the pods + rather than selecting them with -l. A label selector resolves the + pod list once, when the command starts, so a pod being recreated + at that moment is never waited on; a named pod that is missing + fails the command instead, and you rerun it. + - id: await-dataplane-rollout description: >- - For each HA MariaDB patched in the first step, wait for the roll - to finish before continuing: - `kubectl wait mariadb -n - --for=condition=Updated=True --timeout=15m`, then the same with - `--for=condition=Ready=True`. + Wait until the roll has finished, with N the replica count: + `kubectl wait sts -n --timeout=15m + --for=jsonpath='{.status.updatedReplicas}'=N`, then the same with + `--for=jsonpath='{.status.readyReplicas}'=N`. reason: >- - The operator applies the new init and agent images - asynchronously, so reverting the flag while a resource is still - updating strands it on the old data-plane version against a - 26.10.1 operator, which is the skew this record exists to - prevent. Name each resource rather than passing --all: the - Updated condition is absent until an update is triggered, and - kubectl wait does not return early on an absent condition, so a - blanket wait burns the full timeout on every instance that had - no roll to do. + updatedReplicas counts the pods on the StatefulSet's newest + revision, so N updated and N ready is the finished roll. Both + counts mean that only after the steps above: before the new + template exists they already equal N for the old revision. - id: revert-dataplane-autoupdate description: >- kubectl patch mariadb mariadb -n slurm --type merge -p From 73a12e301cc568d45ecbc8bbf26d357d4d2da031 Mon Sep 17 00:00:00 2001 From: Carlos Eduardo Arango Gutierrez Date: Thu, 1 Oct 2026 09:14:11 +0200 Subject: [PATCH 9/9] fix(recipes): commit the data-plane flag in git for GitOps upgrades The GitOps procedure patched autoUpdateDataPlane=true onto the live MariaDB while the desired configuration still said false, and asked the reader to sync promptly. A pruning or self-healing sync restores what git says, and "promptly" does not order it before the upgraded operator's first reconcile. If false wins that race, the operator's Galera and replication defaulting keep the old init and agent images, the data-plane upgrade is skipped, and the image waits time out. The Argo CD and Flux steps now commit true to the desired configuration and sync it before the CRD and operator syncs, confirm the live value, keep it through the image and rollout waits, and only then commit false. The catalog procedure says the same for GitOps users at steps 1 and 5. Signed-off-by: Carlos Eduardo Arango Gutierrez --- docs/user/component-catalog.md | 13 ++++++- .../components/mariadb-operator/upgrades.yaml | 35 ++++++++++++------- 2 files changed, 34 insertions(+), 14 deletions(-) diff --git a/docs/user/component-catalog.md b/docs/user/component-catalog.md index 9504bcda28..412082b96f 100644 --- a/docs/user/component-catalog.md +++ b/docs/user/component-catalog.md @@ -1587,6 +1587,16 @@ CRDs first and the operator second: kubectl patch mariadb mariadb -n slurm --type merge \ -p '{"spec":{"updateStrategy":{"autoUpdateDataPlane":true}}}' ``` + With Argo CD or Flux, do not patch the live resource. Set + `spec.updateStrategy.autoUpdateDataPlane: true` in the desired configuration + the application syncs, commit it, and sync it before step 2, then confirm + the live value with + `kubectl get mariadb -n -o jsonpath='{.spec.updateStrategy.autoUpdateDataPlane}'`. + A pruning or self-healing sync restores whatever git says, and if git still + says `false` when the upgraded operator first reconciles an HA `MariaDB`, + the operator's Galera and replication defaulting keep the old init and + agent images: the data-plane upgrade is skipped and the waits in step 4 + time out. Keep `true` in git until step 4 passes. 2. Upgrade `mariadb-operator-crds` to `26.10.1` **in place**. Confirm which namespace the existing release is in first, because Helm scopes a release by namespace: without `--namespace` the request lands in whatever namespace @@ -1643,7 +1653,8 @@ CRDs first and the operator second: count for the old revision. Skip non-HA instances: they have no init or agent container, so these waits run to their timeout. 5. Return the flag to `false` so a later operator bump does not update the data - plane unattended. If the field is managed in git, set it there. + plane unattended. With Argo CD or Flux, set it back to `false` in the + desired configuration, commit it, and sync, only after step 4 passes. `26.10.0` also changes the operator's default server image to `mariadb:12.3.3`, and `26.10.1` keeps it. AICR pins `mariadb:11.8.8` in diff --git a/recipes/components/mariadb-operator/upgrades.yaml b/recipes/components/mariadb-operator/upgrades.yaml index 59516d2f81..63970423a8 100644 --- a/recipes/components/mariadb-operator/upgrades.yaml +++ b/recipes/components/mariadb-operator/upgrades.yaml @@ -157,15 +157,23 @@ transitions: - steps: - id: enable-dataplane-autoupdate description: >- - kubectl patch mariadb mariadb -n slurm --type merge -p - '{"spec":{"updateStrategy":{"autoUpdateDataPlane":true}}}' + In the desired configuration the Argo CD or Flux application + syncs, set spec.updateStrategy.autoUpdateDataPlane: true on every + HA MariaDB the precondition listed, commit it, and sync that + application before the CRD and operator syncs below. Confirm each + live resource carries it: + `kubectl get mariadb -n + -o jsonpath='{.spec.updateStrategy.autoUpdateDataPlane}'` prints + true. reason: >- - Same upstream requirement, applied out of band before the sync so - it lands ahead of the operator. Repeat for every HA MariaDB the - precondition listed; on a non-HA instance the field is accepted - and does nothing. A pruning Argo CD or Flux configuration will - revert this field on the next sync, so run the sync below - promptly after patching. + Same upstream requirement, and it has to live in git rather than + in a live patch. A pruning or self-healing sync restores whatever + git says, and if git still says false when the upgraded operator + first reconciles an HA MariaDB, the operator's Galera and + replication defaulting keep the old init and agent images: the + data-plane upgrade is skipped and the waits below time out. Keep + true in git until those waits pass. On a non-HA instance the + field is accepted and does nothing. - id: sync-crds description: >- Sync or reconcile the mariadb-operator-crds release to 26.10.1 @@ -232,12 +240,13 @@ transitions: template exists they already equal N for the old revision. - id: revert-dataplane-autoupdate description: >- - kubectl patch mariadb mariadb -n slurm --type merge -p - '{"spec":{"updateStrategy":{"autoUpdateDataPlane":false}}}' + After the waits above pass, set + spec.updateStrategy.autoUpdateDataPlane back to false in the + same desired configuration, commit it, and sync. reason: >- - Upstream recommends returning it to false. If the field is - managed in git, set it there instead so the next sync does not - reintroduce true. + Upstream recommends returning it to false so a later operator + bump does not update the data plane unattended. Do it in git: a + live patch alone is undone by the next sync. references: - https://github.com/mariadb-operator/mariadb-operator/blob/main/docs/releases/UPGRADE_26.10.0.md - https://github.com/mariadb-operator/mariadb-operator/releases/tag/26.10.0