Update rtx6000-vllm.yaml
This commit is contained in:
parent
6df297086c
commit
54267b0818
1 changed files with 4 additions and 4 deletions
|
|
@ -37,14 +37,14 @@ spec:
|
|||
- --port=8000
|
||||
- --tensor-parallel-size=1
|
||||
- --tokenizer-mode=hf
|
||||
- --gpu-memory-utilization=0.90
|
||||
#- --enforce-eager
|
||||
- --gpu-memory-utilization=0.90
|
||||
- --max-model-len=131072
|
||||
- --enable-auto-tool-choice
|
||||
- --kv-cache-dtype=bfloat16
|
||||
- --max-num-batched-tokens=32768
|
||||
- --max-num-seqs=32
|
||||
- --max-num-batched-tokens=65536
|
||||
- --max-num-seqs=64
|
||||
- --block-size=32
|
||||
- --language-model-only
|
||||
- --enable-chunked-prefill
|
||||
- --trust-remote-code
|
||||
- --dtype=auto
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue