Update rtx6000-vllm.yaml

This commit is contained in:
sirius0xdev 2026-05-22 23:39:27 -04:00 committed by GitHub
parent bfd9bbc3b6
commit fa6dd3c8a6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -42,7 +42,7 @@ spec:
- --enable-auto-tool-choice - --enable-auto-tool-choice
- --kv-cache-dtype=bfloat16 - --kv-cache-dtype=bfloat16
- --max-num-batched-tokens=65536 - --max-num-batched-tokens=65536
- --max-num-seqs=64 - --max-num-seqs=32
- --block-size=32 - --block-size=32
- --language-model-only - --language-model-only
- --enable-chunked-prefill - --enable-chunked-prefill