Update rtx6000-vllm.yaml
This commit is contained in:
parent
b536367aea
commit
2b9630d8dc
1 changed files with 2 additions and 2 deletions
|
|
@ -38,11 +38,11 @@ spec:
|
||||||
- --tensor-parallel-size=1
|
- --tensor-parallel-size=1
|
||||||
- --tokenizer-mode=hf
|
- --tokenizer-mode=hf
|
||||||
- --gpu-memory-utilization=0.90
|
- --gpu-memory-utilization=0.90
|
||||||
- --max-model-len=131072
|
- --max-model-len=262144
|
||||||
- --enable-auto-tool-choice
|
- --enable-auto-tool-choice
|
||||||
- --kv-cache-dtype=bfloat16
|
- --kv-cache-dtype=bfloat16
|
||||||
- --max-num-batched-tokens=16384
|
- --max-num-batched-tokens=16384
|
||||||
- --max-num-seqs=64
|
- --max-num-seqs=4
|
||||||
- --block-size=32
|
- --block-size=32
|
||||||
- --language-model-only
|
- --language-model-only
|
||||||
- --enable-chunked-prefill
|
- --enable-chunked-prefill
|
||||||
|
|
|
||||||
Loading…
Add table
Reference in a new issue