flash-attention/flash_attn
2023-09-03 17:57:10 -07:00
..
layers [Rotary] Implement varlen rotary 2023-09-03 17:57:10 -07:00
losses Run isort and black on python files 2023-08-18 14:22:11 -07:00
models [Rotary] Implement rotary in Triton 2023-09-03 02:51:58 -07:00
modules [Rotary] Pass max_seqlen from mha.py to rotary during inference 2023-09-03 11:37:06 -07:00
ops [Rotary] Implement varlen rotary 2023-09-03 17:57:10 -07:00
utils [Gen] Minor fix to modify logits for top_p 2023-08-29 14:29:06 -07:00
__init__.py Update Cutlass to v3.2.0 2023-08-27 23:47:28 -07:00
bert_padding.py add unpad_input_for_concatenated_sequences (#499) 2023-08-29 02:23:56 -07:00
flash_attn_interface.py Change causal mask to be aligned to bottom-right instead of top-left 2023-08-24 23:41:07 -07:00
flash_attn_triton_og.py Run isort and black on python files 2023-08-18 14:22:11 -07:00
flash_attn_triton.py Run isort and black on python files 2023-08-18 14:22:11 -07:00
flash_blocksparse_attention.py Run isort and black on python files 2023-08-18 14:22:11 -07:00
flash_blocksparse_attn_interface.py Run isort and black on python files 2023-08-18 14:22:11 -07:00
fused_softmax.py Run isort and black on python files 2023-08-18 14:22:11 -07:00
pyproject.toml Move pyproject.toml to flash-attn and tests dir to avoid PEP 517 2023-08-25 15:05:28 -07:00