Skip to content

GitLab

Unverified Commit ba99d24a authored by Yan Ru Pei's avatar Yan Ru Pei Committed by GitHub
Browse files

chore: disagg + router k8s recipe minor changes (#4050) 


Signed-off-by: default avatarPeaBrane <yanrpei@gmail.com>
parent e3ba40e8
Show whitespace changes
Inline Side-by-side
Showing with 3 additions and 1 deletion
examples/backends/vllm/deploy/disagg.yaml
View file @ ba99d24a
...@@ -34,6 +34,7 @@ spec: ...@@ -34,6 +34,7 @@ spec:
args: args:
- --model - --model
- Qwen/Qwen3-0.6B - Qwen/Qwen3-0.6B
- --is-decode-worker
VllmPrefillWorker: VllmPrefillWorker:
dynamoNamespace: vllm-disagg dynamoNamespace: vllm-disagg
envFromSecret: hf-token-secret envFromSecret: hf-token-secret
......
examples/backends/vllm/deploy/disagg_router.yaml
View file @ ba99d24a
...@@ -36,11 +36,12 @@ spec: ...@@ -36,11 +36,12 @@ spec:
args: args:
- --model - --model
- Qwen/Qwen3-0.6B - Qwen/Qwen3-0.6B
- --is-decode-worker
VllmPrefillWorker: VllmPrefillWorker:
dynamoNamespace: vllm-v1-disagg-router dynamoNamespace: vllm-v1-disagg-router
envFromSecret: hf-token-secret envFromSecret: hf-token-secret
componentType: worker componentType: worker
replicas: 1 replicas: 2
resources: resources:
limits: limits:
gpu: "1" gpu: "1"
......
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