This website works better with JavaScript
Home
Esplora
Aiuto
Registrati
Accedi
david
/
flash-attention
mirror da
https://github.com/Dao-AILab/flash-attention
Segui
1
Vota
0
Forka
0
File
Problemi
0
Wiki
Ramo (Branch):
main
Rami (Branch)
Tag
changes_for_fp8
decode
doc_masking
fa3-fp8-varlen
fa3-kvcache-gqa
ipiszy/local_attn
ipiszy/used_q
main
tdd
varlen
v2.7.2.post1
v2.7.2
v2.7.1.post4
v2.7.1.post3
v2.7.1.post2
v2.7.1.post1
v2.7.1
v2.7.0.post2
v2.7.0.post1
v2.7.0
v2.6.3
v2.6.2
v2.6.1
v2.6.0.post1
v2.6.0
v2.5.9.post1
v2.5.9
v2.5.8
v2.5.7
v2.5.6
v2.5.5
v2.5.4
v2.5.3
v2.5.2
v2.5.1.post1
v2.5.1
v2.5.0
v2.4.3.post1
v2.4.3
v2.4.2
v2.4.1
v2.4.0.post1
v2.4.0
v2.3.6
v2.3.5
v2.3.4
v2.3.3
v2.3.2
v2.3.1.post1
v2.3.1
v2.3.0
v2.2.5
v2.2.4.post1
v2.2.4
v2.2.3.post2
v2.2.3.post1
v2.2.3
v2.2.2
v2.2.1
v2.2.0
v2.1.2.post3
v2.1.2.post2
v2.1.2.post1
v2.1.2
v2.1.1
v2.1.0
v2.0.9
v2.0.8
v2.0.7
v2.0.6.post2
v2.0.6.post1
v2.0.6
v2.0.5
v2.0.4
v2.0.3
v2.0.2
v2.0.1
v2.0.0
v1.0.9
v1.0.8
v1.0.7
v1.0.6
v1.0.5
v1.0.4
v1.0.3.post0
v1.0.3
v1.0.2
v1.0.1
v1.0.0
v0.2.8
v0.2.7
v0.2.6
v0.2.5
v0.2.4
v0.2.3
v0.2.2
v0.2.1
flash-attention
/
flash_attn
/
modules
SueJane
3f1b4d38e7
Fix: check the type of max_seqlen_k instead of checking max_seqlen twice (
#1127
)
4 mesi fa
..
__init__.py
ece539abd6
Add __init__.py files to subdirectories for installation
2 anni fa
block.py
abbc131173
[LayerNorm] Switch from CUDA to Triton implementation
11 mesi fa
embedding.py
f1a73d0740
Run isort and black on python files
1 anno fa
mha.py
3f1b4d38e7
Fix: check the type of max_seqlen_k instead of checking max_seqlen twice (
#1127
)
4 mesi fa
mlp.py
c3b2196652
Add Alibi to MHA, test with Baichuan-13B
11 mesi fa