Tags: yasyf/infinity
Tags
Merge pull request michaelfeil#339 from michaelfeil/docs-update-qk update docs, bump version
Add flash_attn support (michaelfeil#306) (michaelfeil#313) * Add flash_attn support (michaelfeil#306) * add dockerfile for flash_attn setup * remove test.py * parametrize model name and engine * Update Dockerfile --------- Co-authored-by: Michael Feil <63565275+michaelfeil@users.noreply.github.com> * Delete libs/infinity_emb/Dockerfile.flash --------- Co-authored-by: Göktürk <87906890+gokturkDev@users.noreply.github.com>
api changes sync async (michaelfeil#286) * api: fix minor mismatches * add infer.py