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

Update a100-vllm.yaml

Browse source
This commit is contained in:
sirius0xdev 2026-04-24 22:54:14 -04:00 • committed by GitHub
parent 1ba0ad2dcf
commit ae5e4b5515
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
apps/base/customer1/openclaw/a100-vllm.yaml
View file

@ -39,12 +39,12 @@ spec:
- --tokenizer-mode=hf - --tokenizer-mode=hf
- --gpu-memory-utilization=0.95 - --gpu-memory-utilization=0.95
- --kv-cache-dtype=fp8 - --kv-cache-dtype=fp8
- --max-model-len=auto - --max-model-len=65536
- --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=qwen3_coder - --tool-call-parser=qwen3_xml
- --reasoning-parser=qwen3 - --reasoning-parser=qwen3
- --disable-custom-all-reduce - --disable-custom-all-reduce