fix vllm errors

This commit is contained in:
sirius0xdev 2026-04-18 21:53:00 +00:00
parent 755bdb39ba
commit 197212aacb

View file

@ -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: