Skip to content

fix: do not set default for resources #2471

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Aug 18, 2025
Merged

fix: do not set default for resources #2471

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
6f93925
fix: do not set cpu/mem limit by default
julienmancuso Aug 16, 2025
20141a5
fix: do not set resources by default
julienmancuso Aug 18, 2025
3a658d6
fix: do not set resources by default
julienmancuso Aug 18, 2025
4b71d2b
fix: do not set resources by default
julienmancuso Aug 18, 2025
fb78e6a
fix: do not set resources by default
julienmancuso Aug 18, 2025
bef563c
fix: do not set resources by default
julienmancuso Aug 18, 2025
16868fc
fix: do not set resources by default
julienmancuso Aug 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 0 additions & 13 deletions components/backends/sglang/deploy/agg.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,6 @@ spec:
dynamoNamespace: sglang-agg
componentType: frontend
replicas: 1
resources:
requests:
cpu: "10"
memory: "10Gi"
limits:
cpu: "32"
memory: "40Gi"
extraPodSpec:
mainContainer:
image: my-registry/sglang-runtime:my-tag
Expand All @@ -31,13 +24,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "32"
memory: "80Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand Down
13 changes: 0 additions & 13 deletions components/backends/sglang/deploy/agg_router.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,6 @@ spec:
dynamoNamespace: sglang-agg-router
componentType: frontend
replicas: 1
resources:
requests:
cpu: "10"
memory: "10Gi"
limits:
cpu: "32"
memory: "40Gi"
extraPodSpec:
mainContainer:
image: my-registry/sglang-runtime:my-tag
Expand All @@ -31,13 +24,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "32"
memory: "80Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand Down
10 changes: 0 additions & 10 deletions components/backends/sglang/deploy/disagg-multinode.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,12 +35,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "10"
memory: "40Gi"
limits:
cpu: "10"
memory: "40Gi"
gpu: "4"
extraPodSpec:
mainContainer:
Expand All @@ -67,12 +62,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "10"
memory: "40Gi"
limits:
cpu: "10"
memory: "40Gi"
gpu: "4"
extraPodSpec:
mainContainer:
Expand Down
19 changes: 0 additions & 19 deletions components/backends/sglang/deploy/disagg.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,6 @@ spec:
dynamoNamespace: sglang-disagg
componentType: frontend
replicas: 1
resources:
requests:
cpu: "10"
memory: "10Gi"
limits:
cpu: "32"
memory: "40Gi"
extraPodSpec:
mainContainer:
image: my-registry/sglang-runtime:my-tag
Expand All @@ -31,13 +24,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "32"
memory: "80Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand All @@ -64,13 +51,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "32"
memory: "80Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand Down
33 changes: 0 additions & 33 deletions components/backends/sglang/deploy/disagg_planner.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,13 +18,6 @@ spec:
dynamoNamespace: dynamo
componentType: frontend
replicas: 1
resources:
requests:
cpu: "10"
memory: "10Gi"
limits:
cpu: "32"
memory: "40Gi"
extraPodSpec:
mainContainer:
image: nvcr.io/nvidian/nim-llm-dev/sglang-runtime:hzhou-0811-1
Expand Down Expand Up @@ -56,13 +49,6 @@ spec:
periodSeconds: 60
timeoutSeconds: 30
failureThreshold: 10
resources:
requests:
cpu: "2"
memory: "2Gi"
limits:
cpu: "8"
memory: "16Gi"
pvc:
create: false
name: profiling-pvc # Must be pre-created before deployment and SLA profiler must have been run
Expand Down Expand Up @@ -107,13 +93,6 @@ spec:
periodSeconds: 60
timeoutSeconds: 30
failureThreshold: 10
resources:
requests:
cpu: "2"
memory: "2Gi"
limits:
cpu: "8"
memory: "16Gi"
extraPodSpec:
mainContainer:
image: nvcr.io/nvidian/nim-llm-dev/sglang-runtime:hzhou-0811-1
Expand All @@ -129,13 +108,7 @@ spec:
componentType: worker
replicas: 2
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "32"
memory: "80Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand All @@ -161,13 +134,7 @@ spec:
componentType: worker
replicas: 2
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "32"
memory: "80Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand Down
13 changes: 0 additions & 13 deletions components/backends/trtllm/deploy/agg.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,6 @@ spec:
dynamoNamespace: trtllm-agg
componentType: frontend
replicas: 1
resources:
requests:
cpu: "5"
memory: "10Gi"
limits:
cpu: "5"
memory: "10Gi"
extraPodSpec:
mainContainer:
image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
Expand All @@ -33,13 +26,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "10"
memory: "20Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand Down
6 changes: 0 additions & 6 deletions components/backends/trtllm/deploy/agg_router.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,13 +26,7 @@ spec:
componentType: worker
replicas: 2
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "10"
memory: "20Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand Down
19 changes: 0 additions & 19 deletions components/backends/trtllm/deploy/disagg.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,6 @@ spec:
dynamoNamespace: trtllm-disagg
componentType: frontend
replicas: 1
resources:
requests:
cpu: "5"
memory: "10Gi"
limits:
cpu: "5"
memory: "10Gi"
extraPodSpec:
mainContainer:
image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
Expand All @@ -33,13 +26,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "10"
memory: "20Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand All @@ -56,13 +43,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "10"
memory: "20Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand Down
19 changes: 0 additions & 19 deletions components/backends/trtllm/deploy/disagg_router.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,6 @@ spec:
dynamoNamespace: trtllm-v1-disagg-router
componentType: frontend
replicas: 1
resources:
requests:
cpu: "5"
memory: "10Gi"
limits:
cpu: "5"
memory: "10Gi"
extraPodSpec:
mainContainer:
image: nvcr.io/nvidian/nim-llm-dev/trtllm-runtime:dep-233.17
Expand All @@ -33,13 +26,7 @@ spec:
componentType: worker
replicas: 2
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "10"
memory: "20Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand All @@ -56,13 +43,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "10"
memory: "20Gi"
gpu: "1"
limits:
cpu: "10"
memory: "20Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand Down
3 changes: 3 additions & 0 deletions components/backends/vllm/deploy/agg.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,9 @@ spec:
dynamoNamespace: vllm-agg
componentType: worker
replicas: 1
resources:
limits:
gpu: "1"
extraPodSpec:
mainContainer:
image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:dep-233.17
Expand Down
3 changes: 3 additions & 0 deletions components/backends/vllm/deploy/agg_router.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,9 @@ spec:
replicas: 2
extraPodSpec:
mainContainer:
resources:
limits:
gpu: "1"
image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:dep-233.17
workingDir: /workspace/components/backends/vllm
command:
Expand Down
19 changes: 0 additions & 19 deletions components/backends/vllm/deploy/disagg.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,6 @@ spec:
dynamoNamespace: vllm-disagg
componentType: frontend
replicas: 1
resources:
requests:
cpu: "32"
memory: "10Gi"
limits:
cpu: "32"
memory: "10Gi"
extraPodSpec:
mainContainer:
image: nvcr.io/nvidian/nim-llm-dev/vllm-runtime:dep-233.17
Expand All @@ -33,13 +26,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "32"
memory: "40Gi"
gpu: "1"
limits:
cpu: "32"
memory: "40Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand All @@ -56,13 +43,7 @@ spec:
componentType: worker
replicas: 1
resources:
requests:
cpu: "32"
memory: "40Gi"
gpu: "1"
limits:
cpu: "32"
memory: "40Gi"
gpu: "1"
extraPodSpec:
mainContainer:
Expand Down
Loading
Loading