support tokenised prompt (online vllm)

#17

by Payoto - opened about 10 hours ago

←

Payoto

about 10 hours ago

•

Online vLLM inference passes an already pre-processed text prompt to the multimodal preprocessor.

Payoto

about 10 hours ago

This comment has been hidden

Payoto changed pull request status to open about 9 hours ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment