Could you share scripts for fast inference?

by chujiezheng - opened Apr 8

Apr 8

Thanks for your great work! I am trying to run this 34B RM but find it very slow when loaded by transformers (device_map='auto') and processing long texts (2048). Could you share scripts that enable fast inference, such as using tensor parallel?

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

Tap or paste here to upload images

· Sign up or log in to comment