Update rtx6000-vllm.yaml
This commit is contained in:
parent
fa6dd3c8a6
commit
87c22e71a4
1 changed files with 2 additions and 2 deletions
|
|
@ -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
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue