squall/flash-attention
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
0e8c46ae08
flash-attention/flash_attn
History
Xuechen Li 7fcd3e6a04
map custom model state_dict back to huggingface format (#465) 
* fix name.

* set inv function.

* add map back function.

* handle gqa.

* add type annotation to avoid confusion.

* fix docstr.

* test inverse remap logic.
2023-08-18 20:51:39 -07:00
..
layers Run isort and black on python files 2023-08-18 14:22:11 -07:00
losses Run isort and black on python files 2023-08-18 14:22:11 -07:00
models map custom model state_dict back to huggingface format (#465) 2023-08-18 20:51:39 -07:00
modules Run isort and black on python files 2023-08-18 14:22:11 -07:00
ops Run isort and black on python files 2023-08-18 14:22:11 -07:00
utils Run isort and black on python files 2023-08-18 14:22:11 -07:00
__init__.py Run isort and black on python files 2023-08-18 14:22:11 -07:00
bert_padding.py Run isort and black on python files 2023-08-18 14:22:11 -07:00
flash_attn_interface.py Run isort and black on python files 2023-08-18 14:22:11 -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