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

fix vllm args

Browse source
This commit is contained in:
sirius0xdev 2026-04-18 22:08:56 +00:00
parent 2fbd6bdf81
commit 3a924b4a10
1 changed files with 1 additions and 1 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

@ -44,7 +44,7 @@ spec:
- --disable-custom-all-reduce
- --trust-remote-code
- --dtype=auto
- --limit-mm-per-prompt=image=1,video=0 # Optional: limit vision if not heavily using images yet
- --limit-mm-per-prompt='{"image"=1, "video"=0}' # Optional: limit vision if not heavily using images yet
ports:
- containerPort: 8000
resources: