david/flash-attention

镜像来自 https://github.com/Dao-AILab/flash-attention

作者	SHA1 備註	提交日期
sclarkson	1feb711f46 Fix compilation with clang on ARM64 (#1285)	1 月之前
Tri Dao	e45a46a5b7 [Rotary] Implement GPT-J style (interleaved) rotary	1 年之前
Tri Dao	1e712ea8b0 Implement TensorParallel for MHA	2 年之前
Tri Dao	ca81f32e04 Implement rotary embedding in CUDA	2 年之前