"deploy/helm/vscode:/vscode.git/clone" did not exist on "bfb95df77deda8cc3edb7008de055e6583da3125"
Unverified Commit 412a12a8 authored by Biswa Panda's avatar Biswa Panda Committed by GitHub
Browse files

fix: rm enforce eager from vllm deploy - prefer perf over pod launch time (#2109)

parent 24cb926e
...@@ -86,4 +86,4 @@ spec: ...@@ -86,4 +86,4 @@ spec:
- /bin/sh - /bin/sh
- -c - -c
args: args:
- python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager 2>&1 | tee /tmp/vllm.log - python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B 2>&1 | tee /tmp/vllm.log
...@@ -86,4 +86,4 @@ spec: ...@@ -86,4 +86,4 @@ spec:
- /bin/sh - /bin/sh
- -c - -c
args: args:
- python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager 2>&1 | tee /tmp/vllm.log - python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B 2>&1 | tee /tmp/vllm.log
...@@ -86,7 +86,7 @@ spec: ...@@ -86,7 +86,7 @@ spec:
- /bin/sh - /bin/sh
- -c - -c
args: args:
- "python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager 2>&1 | tee /tmp/vllm.log" - "python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B 2>&1 | tee /tmp/vllm.log"
VllmPrefillWorker: VllmPrefillWorker:
dynamoNamespace: vllm-disagg dynamoNamespace: vllm-disagg
envFromSecret: hf-token-secret envFromSecret: hf-token-secret
...@@ -128,4 +128,4 @@ spec: ...@@ -128,4 +128,4 @@ spec:
- /bin/sh - /bin/sh
- -c - -c
args: args:
- "python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager --is-prefill-worker 2>&1 | tee /tmp/vllm.log" - "python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --is-prefill-worker 2>&1 | tee /tmp/vllm.log"
...@@ -86,7 +86,7 @@ spec: ...@@ -86,7 +86,7 @@ spec:
- /bin/sh - /bin/sh
- -c - -c
args: args:
- "python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager 2>&1 | tee /tmp/vllm.log" - "python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B 2>&1 | tee /tmp/vllm.log"
VllmPrefillWorker: VllmPrefillWorker:
dynamoNamespace: vllm-disagg-planner dynamoNamespace: vllm-disagg-planner
envFromSecret: hf-token-secret envFromSecret: hf-token-secret
...@@ -128,4 +128,4 @@ spec: ...@@ -128,4 +128,4 @@ spec:
- /bin/sh - /bin/sh
- -c - -c
args: args:
- python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager --is-prefill-worker 2>&1 | tee /tmp/vllm.log - python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --is-prefill-worker 2>&1 | tee /tmp/vllm.log
...@@ -86,7 +86,7 @@ spec: ...@@ -86,7 +86,7 @@ spec:
- /bin/sh - /bin/sh
- -c - -c
args: args:
- python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager 2>&1 | tee /tmp/vllm.log - python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B 2>&1 | tee /tmp/vllm.log
VllmPrefillWorker: VllmPrefillWorker:
dynamoNamespace: vllm-v1-disagg-router dynamoNamespace: vllm-v1-disagg-router
envFromSecret: hf-token-secret envFromSecret: hf-token-secret
...@@ -128,4 +128,4 @@ spec: ...@@ -128,4 +128,4 @@ spec:
- /bin/sh - /bin/sh
- -c - -c
args: args:
- python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --enforce-eager --is-prefill-worker 2>&1 | tee /tmp/vllm.log - python3 -m dynamo.vllm --model Qwen/Qwen3-0.6B --is-prefill-worker 2>&1 | tee /tmp/vllm.log
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