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

Update rtx6000-vllm.yaml

Browse source
This commit is contained in:
sirius0xdev 2026-05-02 11:06:22 -04:00 • committed by GitHub
parent 324c69faf9
commit 31e5af495a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml
View file

@ -39,11 +39,11 @@ spec:
- --tensor-parallel-size=1 - --tensor-parallel-size=1
- --tokenizer-mode=hf - --tokenizer-mode=hf
- --gpu-memory-utilization=0.95 - --gpu-memory-utilization=0.95
- --max-model-len=262144 - --max-model-len=131072
- --enable-auto-tool-choice - --enable-auto-tool-choice
- --enable-chunked-prefill - --enable-chunked-prefill
- --max-num-batched-tokens=8192 - --max-num-batched-tokens=4096
- --max-num-seqs=64 - --max-num-seqs=8
- --trust-remote-code - --trust-remote-code
- --dtype=auto - --dtype=auto
- --enable-prefix-caching - --enable-prefix-caching