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

lower num seq

Browse source
This commit is contained in:
sirius0xdev 2026-05-10 02:15:27 +00:00
parent 52f1af7e73
commit a718acffa6
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
infrastructure/gpus/base/vllm-servers/rtx6000-vllm.yaml
View file

@ -42,7 +42,7 @@ spec:
- --enable-auto-tool-choice - --enable-auto-tool-choice
- --kv-cache-dtype=fp8 - --kv-cache-dtype=fp8
- --max-num-batched-tokens=65536 - --max-num-batched-tokens=65536
- --max-num-seqs=128 - --max-num-seqs=64
- --enable-chunked-prefill - --enable-chunked-prefill
- --trust-remote-code - --trust-remote-code
- --dtype=auto - --dtype=auto