mrq b7b99a25f1 added ability to specify attention backend for CLI and webui (because im tired of editing the yaml)		2024-08-26 19:33:51 -05:00
..
arch	added fused_attn (triton-based fused attention) and simply just query for flash_attn under rocm	2024-08-26 19:13:34 -05:00
__init__.py	added ability to specify attention backend for CLI and webui (because im tired of editing the yaml)	2024-08-26 19:33:51 -05:00
ar_nar.py	ughghghhhh	2024-08-09 21:15:01 -05:00
ar.py
base.py	added ability to specify attention backend for CLI and webui (because im tired of editing the yaml)	2024-08-26 19:33:51 -05:00
experimental.py	ughghghhhh	2024-08-09 21:15:01 -05:00
lora.py
nar.py