Add user_vision_size in VLM's get_specializations for chunked embedding in vLLM v1 - #996

Add user_vision_size in VLM's get_specializations for chunked embedding in vLLM v1#996

Rishin Raj (quic-rishinr) merged 6 commits into

qualcomm:release/v1.21.6qualcomm/efficient-transformers:release/v1.21.6from

quic-xiyushi:user_vision_sizequic-xiyushi/efficient-transformers:user_vision_sizeCopy head branch name to clipboard