Shenggui Li fb4c9c3a30 [fix] added support for vlm in offline inference (#3548)

2025-02-15 05:27:29 +08:00

..

engine

…

llava_onevision

…

lora.py

…

openai_batch_chat.py

…

openai_batch_complete.py

…

openai_chat_with_response_prefill.py

…

reward_model.py

…