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

switch image

Browse source
This commit is contained in:
sirius0xdev 2026-04-22 03:00:46 +00:00
parent c236f3c89a
commit 6c4bb798ff
1 changed files with 7 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
apps/base/customer1/openclaw/a100-vllm.yaml
View file

@ -24,7 +24,7 @@ spec:
effect: "NoSchedule" effect: "NoSchedule"
containers: containers:
- name: vllm-brain - name: vllm-brain
image: vllm/vllm-openai:v0.19.1-cu130-ubuntu2404 image: vllm/vllm-openai:v0.19.1-ubuntu2404
command: ["python3", "-m", "vllm.entrypoints.openai.api_server"] command: ["python3", "-m", "vllm.entrypoints.openai.api_server"]
env: env:
- name: HF_TOKEN - name: HF_TOKEN
@ -32,18 +32,20 @@ spec:
- name: VLLM_TOKENIZER_MODE - name: VLLM_TOKENIZER_MODE
value: "auto" value: "auto"
args: args:
- --model=llmfan46/Qwen3.5-35B-A3B-uncensored-heretic - --model=HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive
- --host=0.0.0.0 - --host=0.0.0.0
- --port=8000 - --port=8000
- --tensor-parallel-size=1 - --tensor-parallel-size=1
- --gpu-memory-utilization=0.95 - --gpu-memory-utilization=0.95
- --max-model-len=65536 - --kv-cache-dtype=fp8
- --max-model-len=49152
- --enable-auto-tool-choice - --enable-auto-tool-choice
- --trust-remote-code - --trust-remote-code
- --dtype=auto - --dtype=auto
- --enable-prefix-caching - --enable-prefix-caching
- --tool-call-parser=hermes - --tool-call-parser=hermes
- --enforce-eager - --reasoning-parser=qwen3
- --disable-custom-all-reduce - --disable-custom-all-reduce
ports: ports:
- containerPort: 8000 - containerPort: 8000