We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent e3ba40e commit ba99d24Copy full SHA for ba99d24
examples/backends/vllm/deploy/disagg.yaml
@@ -34,6 +34,7 @@ spec:
34
args:
35
- --model
36
- Qwen/Qwen3-0.6B
37
+ - --is-decode-worker
38
VllmPrefillWorker:
39
dynamoNamespace: vllm-disagg
40
envFromSecret: hf-token-secret
examples/backends/vllm/deploy/disagg_router.yaml
@@ -36,11 +36,12 @@ spec:
41
dynamoNamespace: vllm-v1-disagg-router
42
43
componentType: worker
- replicas: 1
44
+ replicas: 2
45
resources:
46
limits:
47
gpu: "1"
0 commit comments