Update rtx6000-vllm.yaml
This commit is contained in:
parent
87c22e71a4
commit
b3fdb91e13
1 changed files with 1 additions and 1 deletions
|
|
@ -41,7 +41,7 @@ spec:
|
||||||
- --max-model-len=131072
|
- --max-model-len=131072
|
||||||
- --enable-auto-tool-choice
|
- --enable-auto-tool-choice
|
||||||
- --kv-cache-dtype=bfloat16
|
- --kv-cache-dtype=bfloat16
|
||||||
- --max-num-batched-tokens=4096
|
- --max-num-batched-tokens=16384
|
||||||
- --max-num-seqs=64
|
- --max-num-seqs=64
|
||||||
- --block-size=32
|
- --block-size=32
|
||||||
- --language-model-only
|
- --language-model-only
|
||||||
|
|
|
||||||
Loading…
Add table
Reference in a new issue