Releases: Dao-AILab/flash-attention
Releases · Dao-AILab/flash-attention
v2.0.6.post1
Use single thread compilation for cuda12.1, torch2.1 to avoid OOM CI
v2.0.6
Bump to v2.0.6
v1.0.9
Bump to v1.0.9
v1.0.8
Bump to v1.0.8
v1.0.7
Bump version to 1.0.7
v1.0.6
Merge pull request #243 from ksivaman/bump_version_to_v1_0_6 bump to v1.0.6
v1.0.5
Add ninja to pyproject.toml build-system, bump to v1.0.5
v1.0.4
[Docs] Clearer error message for bwd d > 64, bump to v1.0.4
v1.0.3.post0
Bump version to v1.0.3.post0
v1.0.3
Bump version to 1.0.3