fix vllm errors
This commit is contained in:
parent
755bdb39ba
commit
197212aacb
1 changed files with 6 additions and 7 deletions
|
|
@ -34,14 +34,13 @@ spec:
|
|||
args:
|
||||
- "--model"
|
||||
- "Jiunsong/supergemma4-26b-abliterated-multimodal" # Uncensored Abliterated Gemma 26B (Native)
|
||||
- "--dtype"
|
||||
- --dtype=auto
|
||||
- "bfloat16"
|
||||
- "--max-model-len"
|
||||
- "8192"
|
||||
- "--trust-remote-code"
|
||||
- "--gpu-memory-utilization"
|
||||
- "0.95"
|
||||
- "--enforce-eager"
|
||||
- --max-model-len=8192
|
||||
- --trust-remote-code
|
||||
- --gpu-memory-utilization=0.80
|
||||
- --enforce-eager
|
||||
|
||||
ports:
|
||||
- containerPort: 8000
|
||||
resources:
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue