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

fix vllm config

Browse source
This commit is contained in:
sirius0xdev 2026-04-20 01:49:36 +00:00
parent 33495a40d0
commit 0dbf223df0
1 changed files with 4 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

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

@ -36,16 +36,17 @@ spec:
- --host=0.0.0.0
- --port=8000
- --tensor-parallel-size=1
- --gpu-memory-utilization=0.98 # ← Critical: lower than default 0.90
- --gpu-memory-utilization=0.95 # ← Critical: lower than default 0.90
- --max-model-len=24576 # Start conservative (you can raise to 32768 later)
- --max-num-batched-tokens=8192
- --max-num-seqs=16 # Lower for single-user / low-concurrency
- --max-num-seqs=8 # Lower for single-user / low-concurrency
- --enforce-eager # Disables CUDA graphs → big memory saver at startup
- --disable-custom-all-reduce
- --enable-auto-tool-choice
- --trust-remote-code
- --dtype=auto
- --tool-call-parser qwen3_xml
- --tool-call-parser=qwen3_coder
- --reasoning-parser=qwen3
- --enable-prefix-caching
##- --limit-mm-per-prompt='{"image"=1, "video"=0}' # Optional: limit vision if not heavily using images yet
ports: