├── .github └── workflows │ └── run.yml ├── LICENSE ├── README.md ├── bench.py ├── flash_attention_1.cu ├── flash_attention_2.cu └── main.cpp /.github/workflows/run.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/leloykun/flash-attention-minimal/HEAD/.github/workflows/run.yml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/leloykun/flash-attention-minimal/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/leloykun/flash-attention-minimal/HEAD/README.md -------------------------------------------------------------------------------- /bench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/leloykun/flash-attention-minimal/HEAD/bench.py -------------------------------------------------------------------------------- /flash_attention_1.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/leloykun/flash-attention-minimal/HEAD/flash_attention_1.cu -------------------------------------------------------------------------------- /flash_attention_2.cu: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/leloykun/flash-attention-minimal/HEAD/flash_attention_2.cu -------------------------------------------------------------------------------- /main.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/leloykun/flash-attention-minimal/HEAD/main.cpp --------------------------------------------------------------------------------