Will Lin and Claude Fable 5
b9dfb12502
[feat]: register NABLA sparse attention as an attention backend
...
Move nablaT_v2 + the flex-attention guard out of the Kandinsky5 DiT into
fastvideo/attention/backends/nabla.py with backend/metadata/builder/impl
classes, a NABLA_ATTN enum entry, and CUDA platform wiring that refuses to
silently fall back to dense attention when flex_attention is unavailable.
Add a generic default_backend parameter to the selector and LocalAttention —
a layer-level default that the global force and FASTVIDEO_ATTENTION_BACKEND
still override — so nabla checkpoints select the backend by default while
users keep env-var control. The DiT's sparse path now dispatches through a
dedicated LocalAttention (with a direct-flex fallback for standalone parity
tests without a forward context); verified bit-identical to the previous
inline flex call.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-07-05 14:58:12 -07:00
1dee77f4a4
[feat] QAD 5090: Wire the Attn-QAT training attention backend (10/12) ( #1459 )
...
Co-authored-by: William Lin <SolitaryThinker@users.noreply.github.com >
Co-authored-by: Loay Rashid <42599591+loaydatrain@users.noreply.github.com >
Co-authored-by: Kaiqin Kong <k1kong@ucsd.edu >
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
Co-authored-by: alexzms <26690162+alexzms@users.noreply.github.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-17 13:32:56 -07:00
88e753f281
[feat] QAD 5090: Wire the Attn-QAT inference attention backend (8/12) ( #1457 )
...
Co-authored-by: William Lin <SolitaryThinker@users.noreply.github.com >
Co-authored-by: Loay Rashid <42599591+loaydatrain@users.noreply.github.com >
Co-authored-by: Kaiqin Kong <k1kong@ucsd.edu >
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
Co-authored-by: alexzms <26690162+alexzms@users.noreply.github.com >
2026-06-16 13:12:33 -07:00
f6e65ff668
[Feature] Add BSA (Bidirectional Sparse Attention) inference backend ( #1174 )
...
Co-authored-by: Satyam Srivastava <satyam53@Mac.lan1 >
Co-authored-by: Satyam Srivastava <satyam53@Satyams-MacBook-Air.local >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-04-05 05:00:33 +00:00
alexzms
14261bc98c
[feat] pre-commit support 120 col num ( #1167 )
2026-03-11 20:19:30 -07:00
Zhang Peiyuan and Will Lin
fc80d95d7e
[Misc] Remove STA ( #1124 )
...
Co-authored-by: Will Lin <wlsaidhi@gmail.com >
2026-02-23 15:14:42 -08:00
Loay Rashid
dea69cf651
[New Model] Turbodiffusion ( #971 )
2026-01-02 17:55:56 -06:00
Jinzhe Pan and Xingyu Long
f4c58894d9
[Feat] add ray support ( #838 )
...
Co-authored-by: Xingyu Long <xingyulong97@gmail.com >
2025-10-16 23:17:54 -07:00
zyang6 and kiritorl
87489f0872
Add wan2.1 functionality support for Ascend NPU platform ( #810 )
...
Co-authored-by: kiritorl <1021709528@qq.com >
2025-10-09 16:25:08 -07:00
RandNMR73
13d0aae706
Add Sage Attention 3 Backend ( #815 )
2025-09-24 15:11:38 -07:00
Eric Liang and EricLiang
e028dcc7c0
[Backend][Vmoba] Add implementation of VMoba ( #778 )
...
Co-authored-by: EricLiang <https://github.com/EricLina >
2025-09-08 23:53:25 -07:00
Sopiko Kurdadze
5452369749
[Feature] [Inference]Add ROCm platform support for single-gpu inference ( #669 )
2025-07-30 12:57:02 -07:00
William Lin
f572319bd9
[Feature] Remove V1 folder ( #642 )
2025-07-24 22:43:12 -07:00
