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

add tools to vllm

Browse source
This commit is contained in:
sirius0xdev 2026-04-19 23:33:43 +00:00
parent 2d8e4b9476
commit 28e701e27f
1 changed files with 3 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
apps/base/customer1/openclaw/vllm-gemma.yaml
View file

@ -44,6 +44,9 @@ spec:
- --disable-custom-all-reduce - --disable-custom-all-reduce
- --trust-remote-code - --trust-remote-code
- --dtype=auto - --dtype=auto
- --tool-call-parser qwen3_xml
- --reasoning-parser qwen3
- --enable-prefix-caching
##- --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: ports:
- containerPort: 8000 - containerPort: 8000