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

fix: pin vLLM to v0.9.1 and use pythonic tool call parser

Browse source
This commit is contained in:
Sirius Claw 2026-04-20 07:23:43 +00:00
parent bab9d4863e
commit 687d61f626
2 changed files with 4 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
apps/base/customer1/openclaw/vllm-gemma.yaml
View file

@ -24,7 +24,7 @@ spec:
effect: "NoSchedule"
containers:
- name: vllm-brain
image: vllm/vllm-openai:latest
image: vllm/vllm-openai:v0.9.1
command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
env:
- name: HF_TOKEN
@ -41,7 +41,7 @@ spec:
- --enable-auto-tool-choice
- --trust-remote-code
- --dtype=auto
- --tool-call-parser=qwen3_coder
- --tool-call-parser=pythonic
- --reasoning-parser=qwen3
- --enable-prefix-caching
- --enable-chunked-prefill

4
apps/base/customer1/openclaw/vllm-l4.yaml
View file

@ -24,7 +24,7 @@ spec:
effect: "NoSchedule"
containers:
- name: vllm-brain-l4
image: vllm/vllm-openai:latest
image: vllm/vllm-openai:v0.9.1
command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
env:
- name: HF_TOKEN
@ -39,7 +39,7 @@ spec:
- --enable-auto-tool-choice
- --trust-remote-code
- --dtype=auto
- --tool-call-parser=qwen3_coder
- --tool-call-parser=pythonic
- --enable-prefix-caching
ports:
- containerPort: 8000