Update rtx6000-vllm.yaml

This commit is contained in:
sirius0xdev 2026-05-22 23:45:57 -04:00 committed by GitHub
parent fa6dd3c8a6
commit 87c22e71a4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -41,8 +41,8 @@ spec:
- --max-model-len=131072
- --enable-auto-tool-choice
- --kv-cache-dtype=bfloat16
- --max-num-batched-tokens=65536
- --max-num-seqs=32
- --max-num-batched-tokens=4096
- --max-num-seqs=64
- --block-size=32
- --language-model-only
- --enable-chunked-prefill