Unverified Commit 22e6c96f authored by Graham King's avatar Graham King Committed by GitHub
Browse files

chore: Change vllm K8s from dynamo-run to python -m dynamo.frontend (#2055)

parent 9cfaa7be
......@@ -41,12 +41,7 @@ spec:
image: nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
workingDir: /workspace/components/backends/vllm
args:
- dynamo
- run
- in=http
- out=dyn
- --http-port
- "8000"
- "python3 -m dynamo.frontend --http-port 8000"
VllmDecodeWorker:
envFromSecret: hf-token-secret
livenessProbe:
......
......@@ -41,14 +41,7 @@ spec:
image: nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
workingDir: /workspace/components/backends/vllm
args:
- dynamo
- run
- in=http
- out=dyn
- --http-port
- "8000"
- --router-mode
- kv
- "python3 -m dynamo.frontend --http-port 8000 --router-mode kv"
VllmDecodeWorker:
envFromSecret: hf-token-secret
livenessProbe:
......
......@@ -41,12 +41,7 @@ spec:
image: nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
workingDir: /workspace/components/backends/vllm
args:
- dynamo
- run
- in=http
- out=dyn
- --http-port
- "8000"
- "python3 -m dynamo.frontend --http-port 8000"
VllmDecodeWorker:
dynamoNamespace: vllm-v1-disagg
envFromSecret: hf-token-secret
......
......@@ -41,12 +41,7 @@ spec:
image: nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
workingDir: /workspace/components/backends/vllm
args:
- dynamo
- run
- in=http
- out=dyn
- --http-port
- "8000"
- "python3 -m dynamo.frontend --http-port 8000"
VllmDecodeWorker:
dynamoNamespace: vllm-v1-disagg-planner
envFromSecret: hf-token-secret
......
......@@ -41,7 +41,7 @@ spec:
image: nvcr.io/nvidian/nim-llm-dev/vllm_v1-runtime:dep-216.4
workingDir: /workspace/components/backends/vllm
args:
- "python3 -m dynamo.frontend --http-port 8080 --router-mode kv"
- "python3 -m dynamo.frontend --http-port 8000 --router-mode kv"
VllmDecodeWorker:
dynamoNamespace: vllm-v1-disagg-router
envFromSecret: hf-token-secret
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment