alexzms be548a78ea [feat] VSA-256 fastpath on Blackwell via FA4 CuTe block-sparse attention (#1354)

2026-05-26 12:58:29 -07:00

..

__init__.py

[Feature] Remove V1 folder (#642)

2025-07-24 22:43:12 -07:00

abstract.py

[refactor]: shared attention infra additions for QAT-compat (Attn-QAT 5/12) (#1383)

2026-05-23 16:19:24 -07:00

attn_qat_infer.py

[feat]: Attn-QAT inference + training backends (deadcode) (Attn-QAT 4/12) (#1358)

2026-05-22 02:59:25 -07:00

attn_qat_train.py

[feat]: Attn-QAT inference + training backends (deadcode) (Attn-QAT 4/12) (#1358)

2026-05-22 02:59:25 -07:00

bsa_attn.py

[refactor]: shared attention infra additions for QAT-compat (Attn-QAT 5/12) (#1383)

2026-05-23 16:19:24 -07:00

flash_attn.py

[perf]: register FA2/FA3 default flash_attn_func as a torch.library custom op (#1373)

2026-05-23 00:39:06 -07:00

sage_attn3.py

[feat] pre-commit support 120 col num (#1167)

2026-03-11 20:19:30 -07:00

sage_attn.py

[Feature] Remove V1 folder (#642)

2025-07-24 22:43:12 -07:00

sdpa.py

[feat] pre-commit support 120 col num (#1167)

2026-03-11 20:19:30 -07:00

sla.py

[misc] attention hot-path cleanup + denoising loop hoists (#1272)

2026-05-10 11:51:10 -07:00

video_sparse_attn.py

[feat] VSA-256 fastpath on Blackwell via FA4 CuTe block-sparse attention (#1354)

2026-05-26 12:58:29 -07:00

vmoba.py

[refactor]: shared attention infra additions for QAT-compat (Attn-QAT 5/12) (#1383)

2026-05-23 16:19:24 -07:00