Update rtx6000-vllm.yaml
This commit is contained in:
parent
24fee8f4a2
commit
17f46261e0
1 changed files with 2 additions and 2 deletions
|
|
@ -39,12 +39,12 @@ spec:
|
|||
- --tensor-parallel-size=1
|
||||
- --tokenizer-mode=hf
|
||||
- --gpu-memory-utilization=0.95
|
||||
- --kv-cache-dtype=fp8
|
||||
- --kv-cache-dtype=fp8_e5m2
|
||||
- --max-model-len=131072
|
||||
- --enable-auto-tool-choice
|
||||
- --enable-chunked-prefill
|
||||
- --max-num-batched-tokens=8192
|
||||
- --max-num-seqs=4
|
||||
- --max-num-seqs=64
|
||||
- --trust-remote-code
|
||||
- --dtype=auto
|
||||
- --enable-prefix-caching
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue