chore: add ephemeral-storage requests to deploy profiles (#6723)

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>

.github/workflows/pr.yaml

@@ -297,7 +297,12 @@ jobs:
    # ============================================================================
   deploy-test-vllm:
     # Run if core, vllm, or deploy is changed
-    if: needs.changed-files.outputs.core == 'true' || needs.changed-files.outputs.vllm == 'true' || needs.changed-files.outputs.deploy == 'true'
+    # always() is needed because reusable workflows with skipped internal jobs
+    # (e.g. multi-gpu tests, arm64 copy) cause GitHub Actions to skip dependent
+    # jobs unless always() is present. !failure() ensures we still skip on real failures.
+    if: |
+      always() && !failure() &&
+      (needs.changed-files.outputs.core == 'true' || needs.changed-files.outputs.vllm == 'true' || needs.changed-files.outputs.deploy == 'true')
     runs-on: prod-default-small-v2
     needs: [changed-files, deploy-operator, vllm-pipeline]
     timeout-minutes: 25
@@ -334,8 +339,10 @@ jobs:
 
   deploy-test-sglang:
     runs-on: prod-default-small-v2
-    # Run if core, sglang, or deploy is changed
-    if: needs.changed-files.outputs.core == 'true' || needs.changed-files.outputs.sglang == 'true' || needs.changed-files.outputs.deploy == 'true'
+    # Run if core, sglang, or deploy is changed (see deploy-test-vllm for always() rationale)
+    if: |
+      always() && !failure() &&
+      (needs.changed-files.outputs.core == 'true' || needs.changed-files.outputs.sglang == 'true' || needs.changed-files.outputs.deploy == 'true')
     needs: [changed-files, deploy-operator, sglang-pipeline]
     timeout-minutes: 25
     permissions:
@@ -369,8 +376,10 @@ jobs:
 
   deploy-test-trtllm:
     runs-on: prod-default-small-v2
-    # Run if core, trtllm, or deploy is changed
-    if: needs.changed-files.outputs.core == 'true' || needs.changed-files.outputs.trtllm == 'true' || needs.changed-files.outputs.deploy == 'true'
+    # Run if core, trtllm, or deploy is changed (see deploy-test-vllm for always() rationale)
+    if: |
+      always() && !failure() &&
+      (needs.changed-files.outputs.core == 'true' || needs.changed-files.outputs.trtllm == 'true' || needs.changed-files.outputs.deploy == 'true')
     needs: [changed-files, deploy-operator, trtllm-pipeline]
     timeout-minutes: 25
     permissions:

examples/backends/sglang/deploy/agg.yaml

@@ -20,6 +20,10 @@ spec:
       resources:
         limits:
           gpu: "1"
+        requests:
+          custom:
+            # Increase this value for larger models
+            ephemeral-storage: "2Gi"
       extraPodSpec:
         mainContainer:
           image: my-registry/sglang-runtime:my-tag

examples/backends/sglang/deploy/agg_router.yaml

@@ -23,6 +23,10 @@ spec:
       resources:
         limits:
           gpu: "1"
+        requests:
+          custom:
+            # Increase this value for larger models
+            ephemeral-storage: "2Gi"
       extraPodSpec:
         mainContainer:
           image: my-registry/sglang-runtime:my-tag

examples/backends/trtllm/deploy/agg.yaml

@@ -20,6 +20,10 @@ spec:
       resources:
         limits:
           gpu: "1"
+        requests:
+          custom:
+            # Increase this value for larger models
+            ephemeral-storage: "2Gi"
       extraPodSpec:
         mainContainer:
           image: my-registry/tensorrtllm-runtime:my-tag

examples/backends/trtllm/deploy/agg_router.yaml

@@ -23,6 +23,10 @@ spec:
       resources:
         limits:
           gpu: "1"
+        requests:
+          custom:
+            # Increase this value for larger models
+            ephemeral-storage: "2Gi"
       extraPodSpec:
         mainContainer:
           image: my-registry/tensorrtllm-runtime:my-tag

examples/backends/vllm/deploy/agg.yaml

@@ -21,6 +21,10 @@ spec:
       resources:
         limits:
           gpu: "1"
+        requests:
+          custom:
+            # Increase this value for larger models
+            ephemeral-storage: "2Gi"
       extraPodSpec:
         mainContainer:
           image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag

examples/backends/vllm/deploy/agg_router.yaml

@@ -23,6 +23,10 @@ spec:
       resources:
         limits:
           gpu: "1"
+        requests:
+          custom:
+            # Increase this value for larger models
+            ephemeral-storage: "2Gi"
       extraPodSpec:
         mainContainer:
           image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag

examples/backends/vllm/deploy/disagg.yaml

@@ -21,6 +21,10 @@ spec:
       resources:
         limits:
           gpu: "1"
+        requests:
+          custom:
+            # Increase this value for larger models
+            ephemeral-storage: "2Gi"
       extraPodSpec:
         mainContainer:
           image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
@@ -42,6 +46,10 @@ spec:
       resources:
         limits:
           gpu: "1"
+        requests:
+          custom:
+            # Increase this value for larger models
+            ephemeral-storage: "2Gi"
       extraPodSpec:
         mainContainer:
           image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag

examples/backends/vllm/deploy/disagg_router.yaml

@@ -23,6 +23,10 @@ spec:
       resources:
         limits:
           gpu: "1"
+        requests:
+          custom:
+            # Increase this value for larger models
+            ephemeral-storage: "2Gi"
       extraPodSpec:
         mainContainer:
           image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag
@@ -43,6 +47,10 @@ spec:
       resources:
         limits:
           gpu: "1"
+        requests:
+          custom:
+            # Increase this value for larger models
+            ephemeral-storage: "2Gi"
       extraPodSpec:
         mainContainer:
           image: nvcr.io/nvidia/ai-dynamo/vllm-runtime:my-tag