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

fix vllm error

Browse source
This commit is contained in:
sirius0xdev 2026-04-21 01:49:00 +00:00
parent d109eba378
commit 25fc06accf
1 changed files with 5 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
apps/base/customer1/openclaw/vllm-l4.yaml
View file

@ -29,6 +29,8 @@ spec:
env: env:
- name: HF_TOKEN - name: HF_TOKEN
value: "" value: ""
- name: VLLM_LOGGING_LEVEL
value: DEBUG
args: args:
- --model=cognitivecomputations/dolphin-2.9.3-qwen2-7b-awq - --model=cognitivecomputations/dolphin-2.9.3-qwen2-7b-awq
- --quantization=awq - --quantization=awq
@ -40,14 +42,15 @@ spec:
- --enable-auto-tool-choice - --enable-auto-tool-choice
- --trust-remote-code - --trust-remote-code
- --dtype=auto - --dtype=auto
- --tool-call-parser=pythonic - --tool-call-parser hermes
- --enable-prefix-caching - --enable-prefix-caching
ports: ports:
- containerPort: 8000 - containerPort: 8000
resources: resources:
limits: limits:
nvidia.com/gpu: 1 nvidia.com/gpu: 1
memory: "24Gi" memory: "30Gi"
cpu: "8" cpu: "8"
requests: requests:
nvidia.com/gpu: 1 nvidia.com/gpu: 1