From 6c41be6d12e58c9def925e5e20f19d810428be08 Mon Sep 17 00:00:00 2001 From: Harrison King Saturley-Hall Date: Thu, 28 May 2026 21:20:57 -0400 Subject: [PATCH] chore(release): bump example and helm image tags to 0.4.0 Release housekeeping deferred until the 0.4.0 branch was cut. Bumps the modelexpress-server NGC image tag from 0.3.0 to 0.4.0 in: - 6 example Kubernetes manifests under examples/ - 4 Helm values files (values.yaml, values-{development,production}.yaml, test-values.yaml) and 2 references in helm/README.md Chart.yaml was already on 0.4.0; only the image-tag defaults inside the values files were stale. Co-Authored-By: Claude Opus 4.7 --- examples/dynamo_model_cache_k8s/agg.yaml | 2 +- .../vllm/vllm-multi-node-aggregated.yaml | 2 +- .../vllm/vllm-single-node-disaggregated.yaml | 2 +- examples/p2p_transfer_k8s/client/trtllm/mx-infra-decode.yaml | 2 +- .../kubernetes_backend/modelexpress-server-kubernetes.yaml | 2 +- .../server/redis_backend/modelexpress-server-redis.yaml | 2 +- helm/README.md | 4 ++-- helm/test-values.yaml | 2 +- helm/values-development.yaml | 2 +- helm/values-production.yaml | 2 +- helm/values.yaml | 2 +- 11 files changed, 12 insertions(+), 12 deletions(-) diff --git a/examples/dynamo_model_cache_k8s/agg.yaml b/examples/dynamo_model_cache_k8s/agg.yaml index cd221a10..f1978a3b 100644 --- a/examples/dynamo_model_cache_k8s/agg.yaml +++ b/examples/dynamo_model_cache_k8s/agg.yaml @@ -97,7 +97,7 @@ spec: runAsGroup: 1000 fsGroup: 1000 mainContainer: - image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.3.0 + image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.4.0 imagePullPolicy: IfNotPresent env: - name: MODEL_EXPRESS_SERVER_PORT diff --git a/examples/dynamo_p2p_transfer_k8s/vllm/vllm-multi-node-aggregated.yaml b/examples/dynamo_p2p_transfer_k8s/vllm/vllm-multi-node-aggregated.yaml index 4e7a1d9f..005cab60 100644 --- a/examples/dynamo_p2p_transfer_k8s/vllm/vllm-multi-node-aggregated.yaml +++ b/examples/dynamo_p2p_transfer_k8s/vllm/vllm-multi-node-aggregated.yaml @@ -49,7 +49,7 @@ spec: extraPodSpec: serviceAccountName: modelexpress mainContainer: - image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.3.0 + image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.4.0 command: - /bin/sh - -c diff --git a/examples/dynamo_p2p_transfer_k8s/vllm/vllm-single-node-disaggregated.yaml b/examples/dynamo_p2p_transfer_k8s/vllm/vllm-single-node-disaggregated.yaml index 2c47bbc3..be6c13bc 100644 --- a/examples/dynamo_p2p_transfer_k8s/vllm/vllm-single-node-disaggregated.yaml +++ b/examples/dynamo_p2p_transfer_k8s/vllm/vllm-single-node-disaggregated.yaml @@ -43,7 +43,7 @@ spec: extraPodSpec: serviceAccountName: modelexpress mainContainer: - image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.3.0 + image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.4.0 command: - /bin/sh - -c diff --git a/examples/p2p_transfer_k8s/client/trtllm/mx-infra-decode.yaml b/examples/p2p_transfer_k8s/client/trtllm/mx-infra-decode.yaml index ae27f85d..db09561c 100644 --- a/examples/p2p_transfer_k8s/client/trtllm/mx-infra-decode.yaml +++ b/examples/p2p_transfer_k8s/client/trtllm/mx-infra-decode.yaml @@ -77,7 +77,7 @@ spec: effect: NoExecute containers: - name: server - image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.3.0 + image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.4.0 ports: - containerPort: 8001 env: diff --git a/examples/p2p_transfer_k8s/server/kubernetes_backend/modelexpress-server-kubernetes.yaml b/examples/p2p_transfer_k8s/server/kubernetes_backend/modelexpress-server-kubernetes.yaml index 5e28a9d0..e84cf93b 100644 --- a/examples/p2p_transfer_k8s/server/kubernetes_backend/modelexpress-server-kubernetes.yaml +++ b/examples/p2p_transfer_k8s/server/kubernetes_backend/modelexpress-server-kubernetes.yaml @@ -41,7 +41,7 @@ spec: serviceAccountName: modelexpress containers: - name: modelexpress-server - image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.3.0 + image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.4.0 imagePullPolicy: IfNotPresent ports: - containerPort: 8001 diff --git a/examples/p2p_transfer_k8s/server/redis_backend/modelexpress-server-redis.yaml b/examples/p2p_transfer_k8s/server/redis_backend/modelexpress-server-redis.yaml index 65cdd691..85e6a9f8 100644 --- a/examples/p2p_transfer_k8s/server/redis_backend/modelexpress-server-redis.yaml +++ b/examples/p2p_transfer_k8s/server/redis_backend/modelexpress-server-redis.yaml @@ -75,7 +75,7 @@ spec: containers: - name: modelexpress-server - image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.3.0 + image: nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.4.0 imagePullPolicy: Always ports: - containerPort: 8001 diff --git a/helm/README.md b/helm/README.md index 0632f31a..a2f10cef 100644 --- a/helm/README.md +++ b/helm/README.md @@ -101,7 +101,7 @@ The following table lists the configurable parameters of the ModelExpress chart | `replicaCount` | Number of ModelExpress replicas | `1` | | `image.repository` | ModelExpress image repository | `nvcr.io/nvidia/ai-dynamo/modelexpress-server` | | `image.pullPolicy` | Image pull policy | `IfNotPresent` | -| `image.tag` | ModelExpress image tag | `0.3.0` | +| `image.tag` | ModelExpress image tag | `0.4.0` | | `imagePullSecrets` | Image pull secrets for nvcr.io access | `[]` | | `nameOverride` | Override the chart name | `""` | | `fullnameOverride` | Override the full app name | `""` | @@ -295,7 +295,7 @@ The Helm chart uses the official NVIDIA ModelExpress image from the NVIDIA Conta docker login nvcr.io -u '$oauthtoken' -p 'YOUR_NVCR_API_KEY' # Pull the image -docker pull nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.3.0 +docker pull nvcr.io/nvidia/ai-dynamo/modelexpress-server:0.4.0 ``` **Note:** The default image requires authentication. See the [Installation](#installation) section for creating the required Kubernetes secret. diff --git a/helm/test-values.yaml b/helm/test-values.yaml index 36b238b3..092ef1a1 100644 --- a/helm/test-values.yaml +++ b/helm/test-values.yaml @@ -7,7 +7,7 @@ replicaCount: 1 image: repository: nvcr.io/nvidia/ai-dynamo/modelexpress-server pullPolicy: IfNotPresent - tag: "0.3.0" + tag: "0.4.0" serviceAccount: create: true diff --git a/helm/values-development.yaml b/helm/values-development.yaml index 16ad0577..a225f528 100644 --- a/helm/values-development.yaml +++ b/helm/values-development.yaml @@ -7,7 +7,7 @@ replicaCount: 1 image: repository: nvcr.io/nvidia/ai-dynamo/modelexpress-server pullPolicy: IfNotPresent - tag: "0.3.0" + tag: "0.4.0" serviceAccount: create: true diff --git a/helm/values-production.yaml b/helm/values-production.yaml index e735eb2b..6ac14635 100644 --- a/helm/values-production.yaml +++ b/helm/values-production.yaml @@ -7,7 +7,7 @@ replicaCount: 3 image: repository: nvcr.io/nvidia/ai-dynamo/modelexpress-server pullPolicy: Always - tag: "0.3.0" + tag: "0.4.0" serviceAccount: create: true diff --git a/helm/values.yaml b/helm/values.yaml index f2533e15..4bbd69f0 100644 --- a/helm/values.yaml +++ b/helm/values.yaml @@ -10,7 +10,7 @@ replicaCount: 1 image: repository: nvcr.io/nvidia/ai-dynamo/modelexpress-server pullPolicy: IfNotPresent - tag: "0.3.0" + tag: "0.4.0" imagePullSecrets: - name: nvcr-secret