sirius/gcloud-lab
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix: revert vLLM image to latest to support qwen3_coder tool parser

Browse source
This commit is contained in:
Sirius Claw 2026-04-20 07:16:42 +00:00
parent ec5eecf723
commit baa88975b5
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
apps/base/customer1/openclaw/vllm-gemma.yaml
View file

@ -24,7 +24,7 @@ spec:
effect: "NoSchedule" effect: "NoSchedule"
containers: containers:
- name: vllm-brain - name: vllm-brain
image: vllm/vllm-openai:v0.7.3 image: vllm/vllm-openai:latest
command: ["python3", "-m", "vllm.entrypoints.openai.api_server"] command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
env: env:
- name: HF_TOKEN - name: HF_TOKEN

2
apps/base/customer1/openclaw/vllm-l4.yaml
View file

@ -24,7 +24,7 @@ spec:
effect: "NoSchedule" effect: "NoSchedule"
containers: containers:
- name: vllm-brain-l4 - name: vllm-brain-l4
image: vllm/vllm-openai:v0.7.3 image: vllm/vllm-openai:latest
command: ["python3", "-m", "vllm.entrypoints.openai.api_server"] command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
env: env:
- name: HF_TOKEN - name: HF_TOKEN