Commit Graph
27 Commits
Author SHA1 Message Date
William Lin f9e3680f11 [perf] Align FastH3 optimized inference profile (#1748) 2026-08-23 02:01:03 -07:00
William Lin 604e0205a4 [perf] Keep odd MiniMax-H3 VSA tiles on sm100a (#1745) 2026-08-22 18:29:30 -07:00
William Lin c488fa1211 [perf] Add opt-in packed-varlen FA4 for MiniMax-H3 (#1742) 2026-08-22 17:16:47 -07:00
Junda Su 2f3d407406 [perf] Optimize MiniMax H3 VAE decoding (#1734) 2026-08-21 14:57:32 -07:00
William Lin 6d6a10be7a [feat] FastVideo-Minimax-FastH3-Preview few-step example + 64-token-tile VSA-H3 inference path (#1731) 2026-08-21 12:40:09 -05:00
00338aa9ca [perf] Add FA4 CuTe backward support for VSA-256 (#1639)
Co-authored-by: Hyunsung Lee <hyunsungl@sizigistudios.com>
Co-authored-by: alexzms <3036648523@qq.com>
2026-08-19 11:46:49 -07:00
Kai 0653f8f3af [new-model] Add V2A: native MMAudio inference pipeline (#1622) 2026-08-09 17:29:27 -07:00
William Lin e0d702decb [feat] VSA for MiniMax H3: packed mixed-modality sparse attention (#1695) 2026-08-09 13:10:51 -07:00
William Lin 9028953625 [misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702) 2026-08-08 22:24:17 -07:00
William Lin b963a24612 [bugfix]: hard-fail when ATTN_QAT_INFER is selected but the kernel is unusable (#1690) 2026-08-06 13:12:27 -07:00
William Lin b9be2449dc [refactor]: delete the dead global attention-backend override (#1672) 2026-08-02 18:00:42 -07:00
William Lin 7b094c945b [refactor]: resolve attention backend once per component at load time (#1657) 2026-08-02 15:07:42 -07:00
William Lin af2934dd6b [feat]: FA4-FP4 ATTN_QAT_INFER on sm_100/sm_103 + NVFP4 weight purge (#1647) 2026-07-27 15:46:52 -07:00
William Lin bf18371afe [feat] Enable LTX-2 NVFP4 linear and attention QAT fine-tuning (#1626) 2026-07-26 02:19:34 -07:00
Adriel FungandSolitaryThinker 521dee0e82 [perf]: enable per-block torch.compile for LTX2 with persistent cache (#1602)
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
2026-07-20 15:59:13 -07:00
9709b7513b [feat] Port NVFP4 QAT/QAD to modular train framework (#1619)
Co-authored-by: Peiyuan Zhang <email>

Co-authored-by: Peiyuan <a>
2026-07-18 15:01:09 -07:00
William Lin 821e5a0832 [bugfix]: fix FlashAttention resolver tests after tuple return (#1597) 2026-07-13 16:29:03 -07:00
William Lin c1abc42782 [bugfix]: allow unrestricted head sizes in SDPA (#1596) 2026-07-13 16:04:51 -07:00
Raghav K 055586703d [perf]: register a real backward for FA2 default + masked/varlen custom ops (training-under-compile) (#1388) 2026-07-12 00:45:27 +00:00
02e1143f22 [feat] Add Kandinsky-5 T2V/I2V pipeline support (#1471)
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: leffff <levnovitskiy@gmail.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
2026-07-07 14:43:30 -07:00
William Lin a5a6d171e5 [attn] Make FA4 explicit opt-in via FASTVIDEO_FA4 and delete the runtime fallback machinery (#1540) 2026-07-04 14:51:00 -07:00
Mac Lee 00ec3e7388 [bugfix]: compute VSA topk from padded blocks (#1517) 2026-07-03 14:16:51 -07:00
William Lin 78d606a3a7 [feat]: make VSA tile cache configurable for training (#1444) 2026-06-28 02:18:31 -07:00
19a838f54f [bugfix]: release VSA tile cache during training (#1434)
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-09 15:01:22 -07:00
William Lin ba75ad82db [refactor]: shared attention infra additions for QAT-compat (Attn-QAT 5/12) (#1383) 2026-05-23 16:19:24 -07:00
2f3ca8aaad [perf]: register FA2/FA3 default flash_attn_func as a torch.library custom op (#1373)
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
2026-05-23 00:39:06 -07:00
XOR-op 95066245db [misc] FlashAttention 4 support (#1114) 2026-03-07 16:53:43 -08:00