| .. |
|
layers
|
3566596ad8
Fix typo in RotaryEmbedding forward output type (#666)
|
1 jaar geleden |
|
losses
|
ec6d22143b
[CrossEntropy] Change ignored_index -> ignore_index
|
7 maanden geleden |
|
models
|
0d810cfb73
Fix KeyError handling for non-existing key in state_dict.pop() (#898)
|
5 maanden geleden |
|
modules
|
6bbc532388
fix: cast the alibi slopes to torch.float32 (#846)
|
9 maanden geleden |
|
ops
|
22339db185
remove an unused import (#960)
|
6 maanden geleden |
|
utils
|
320fb59487
Update citation
|
6 maanden geleden |
|
__init__.py
|
59594f2a67
Bump to v2.6.2
|
4 maanden geleden |
|
bert_padding.py
|
c94cd09744
Updated missing docstrings for args and returns in bert_padding.py (#795)
|
10 maanden geleden |
|
flash_attn_interface.py
|
ef3e358a25
remove lambda (#1056)
|
4 maanden geleden |
|
flash_attn_triton.py
|
f1a73d0740
Run isort and black on python files
|
1 jaar geleden |
|
flash_attn_triton_og.py
|
f1a73d0740
Run isort and black on python files
|
1 jaar geleden |
|
flash_blocksparse_attention.py
|
f1a73d0740
Run isort and black on python files
|
1 jaar geleden |
|
flash_blocksparse_attn_interface.py
|
f1a73d0740
Run isort and black on python files
|
1 jaar geleden |
|
fused_softmax.py
|
f1a73d0740
Run isort and black on python files
|
1 jaar geleden |
|
pyproject.toml
|
73bd3f3bbb
Move pyproject.toml to flash-attn and tests dir to avoid PEP 517
|
1 jaar geleden |
Tri Dao
59594f2a67
Bump to v2.6.2