mrq 0d706ec6a1 added fused_attn (triton-based fused attention) and simply just query for flash_attn under rocm		2024-08-26 19:13:34 -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
ar_nar.py
ar.py
base.py	added fused_attn (triton-based fused attention) and simply just query for flash_attn under rocm	2024-08-26 19:13:34 -05:00
experimental.py
lora.py
nar.py