Aryan Kumar
881400490c
[bugfix]: stabilize fastcheck lanes for Kandinsky PR
2026-07-06 11:42:26 -07:00
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
Will Lin and Claude Fable 5
9472ed0aab
[bugfix]: surface kandinsky5 flex-attention failures and preserve rotary dtype
...
Replace the bare except around the flex_attention import (which swallowed
every error, printed blank lines to stdout, and silently degraded NABLA
requests to dense attention over ~95k tokens) with except ImportError plus a
logger warning, and raise a RuntimeError when sparse attention is requested
without flex_attention, matching the reference implementation. Also restore
the input dtype in _apply_rotary instead of hard-casting to bf16, which
truncated fp32 q/k through a bf16 round-trip in fp32/parity runs.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-07-05 14:58:12 -07:00
leffff
d39e2e9fd7
fix nabla attention
2026-07-05 14:58:12 -07:00
leffff
a66fb26781
add nabla
2026-07-05 14:58:12 -07:00
Aryan Kumar
0ce6dc928f
[feat]: add kandinsky5 pipeline support
2026-07-05 14:58:12 -07:00
Mac Lee and SolitaryThinker
31aa115611
[bugfix]: preserve FSDP hooks for RMSNorm qk norms ( #1513 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-07-05 04:15:49 +00:00
William Lin
b36d0ef085
[infra] Add DGX Spark and multi-architecture CUDA support ( #1447 )
2026-07-03 13:41:43 -07:00
William Lin
c4e108de78
[docs]: modernize documentation build ( #1503 )
2026-06-28 02:02:09 -07:00
Kaiqin Kong
16bf2eaf77
[feat] Relativistic RoPE re-indexing for long causal rollouts ( #1454 )
2026-06-28 01:43:00 -07:00
d922ab2cbc
[model] Flux2 Klein Port ( #1349 )
...
Co-authored-by: Gnav3852 <63612880+Gnav3852@users.noreply.github.com >
Co-authored-by: Mac Lee <macthecadillac@gmail.com >
2026-06-09 14:55:55 -07:00
2e35b0c6bd
[refactor]: linear/mlp FP4 path additions for Wan-2.1 (Attn-QAT 6/12) ( #1390 )
...
Co-authored-by: Peiyuan Zhang <a1286225768@gmail.com >
Co-authored-by: Matthew Noto <notomatthew31@gmail.com >
2026-06-08 14:51:57 -07:00
Shao Duan and SolitaryThinker
570607945c
[feat] dreamverse: sequence parallelism for serving ( #1424 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-06-01 23:13:49 -07:00
Kaiqin Kong
3f24578139
[bugfix] LTX2: honor video_position_offset_sec in the DiT ( #1422 )
2026-06-01 16:59:15 -07:00
alexzms and mergify[bot]
c2d7143c72
[feat] LTX-2.3 transformer support (config-gated extension of LTX-2) ( #1397 )
...
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-05-29 16:42:37 -07:00
Kaiqin Kong and SolitaryThinker
afdb6fbfa5
[feat] Add MatrixGame3.0 ( #1201 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-05-27 21:07:01 +00:00
Mingjia Huo
63030cf6ec
[fix] Fix causal self-forcing attention settings ( #1355 )
2026-05-17 22:59:47 -07:00
Kaiqin Kong and mergify[bot]
773d44b875
[misc] Rename MatrixGame to MatrixGame2 ( #1357 )
...
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-05-17 22:57:03 -07:00
b4de5a9f1b
[feat] Dreamverse 12/14: Add LTX2 refine and upsampler support ( #1335 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
Co-authored-by: Matthew Noto <99706358+RandNMR73@users.noreply.github.com >
Co-authored-by: XOR-op <17672363+XOR-op@users.noreply.github.com >
Co-authored-by: Zhang Peiyuan <42993249+jzhang38@users.noreply.github.com >
2026-05-15 12:21:40 -07:00
William Lin
de803cb250
[feat]: MagiHuman DiT (transformer) port + parity tests (3/8) ( #1297 )
2026-05-12 14:49:03 -07:00
Raghav K
9d0af28307
[feat] Add Cosmos 2.5 T2W training pipeline (LoRA + full fine-tune) ( #1227 )
2026-05-11 19:15:00 -07:00
d6dfe95466
[feat] FastVideo World Model Training ( #1179 )
...
Co-authored-by: mignonjia <mhuo@ucsd.edu >
Co-authored-by: alexzms <3036648523@qq.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-05-11 05:13:12 +00:00
f633e30ebb
[feat]: add LongCat bidirectional finetuning support ( #1244 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
Co-authored-by: alexzms <3036648523@qq.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-05-09 12:20:43 -07:00
William Lin
c77a76c6af
[feat] Stable Audio Open 1.0: T2A + A2A + RePaint inpainting (native) ( #1260 )
2026-05-01 00:07:11 -07:00
alexzms
d14d5aadea
[feat] Cosmos 2.5 training support in fastvideo.train ( #1224 )
2026-05-01 01:15:02 +00:00
vishruthb
5789955bbe
[feat] add gen3c (cosmos-7b) model and pipeline support ( #1059 )
2026-04-01 11:42:02 +00:00
jaisurya27
4d49f7b0aa
Kandinsky5 lite dit clean ( #1088 )
2026-03-26 08:07:11 +08:00
alexzms
14261bc98c
[feat] pre-commit support 120 col num ( #1167 )
2026-03-11 20:19:30 -07:00
Zhang Peiyuan
cd1b7cf139
[Refactor] SP Mask --> original seq len; HunyuanVideo 1.5 does not need mask ( #1142 )
2026-03-04 11:44:47 +08:00
Zhang Peiyuan
d902967208
Py/fix sp ( #1138 )
2026-02-27 12:14:44 +08:00
William Lin
69dd3c68f6
[bugfix] fix matrix game kv indexing and CI ( #1135 )
2026-02-26 01:24:42 -08:00
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
Shao Duan and SolitaryThinker
37cab18780
[bugfix] Added ltx2 guidance missing modulation term ( #1100 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-02-23 14:22:31 -08:00
Zhang Peiyuan
128d0b7fc5
[Misc] Remove Teacache ( #1121 )
2026-02-22 16:53:07 -08:00
Zhang Peiyuan
03d9ce2edb
[Misc] Remove StepVideo ( #1118 )
2026-02-21 17:15:42 -08:00
10fc92dba5
Upstream LTX2 Training ( #1116 )
...
Co-authored-by: RandNMR73 <notomatthew31@gmail.com >
Co-authored-by: JerryZhou54 <zhouw.jerry2017@outlook.com >
Co-authored-by: Davids048 <jundasu@ucsd.edu >
Co-authored-by: Peiyuan Zhang <a1286225768@slurm-h200-204-239.slurm-compute.tenant-slurm.svc.cluster.local >
2026-02-21 16:06:55 -08:00
8e39ce38c9
[Feat] Native dit implementation for SD3.5 ( #1093 )
...
Co-authored-by: Ishan Vaish <vaish.ishan@gmail.com >
Co-authored-by: Cursor <cursoragent@cursor.com >
2026-02-18 10:19:40 +08:00
XOR-op
959dbcc8a2
[perf] causal MatrixGame optimization ( #1078 )
2026-02-15 09:51:00 +08:00
Mihir Jagtap
7a83e0e6fc
[feature] Add Hunyuan-GameCraft model support ( #1071 )
2026-02-14 08:07:44 +08:00
Shao Duan and Will Lin
7f795600c8
[bugfix] Fixed ltx2 base cfg guidance ( #1095 )
...
Co-authored-by: Will Lin <wlsaidhi@gmail.com >
2026-02-13 11:53:11 -08:00
Kaiqin Kong
31c0f1b341
[feat] Port LingBot-World-Base (Cam) ( #1081 )
2026-02-10 11:12:33 -08:00
Ishan and Jinzhe Pan
0aff68f51d
[Feat] Add Stable Diffusion 3.5 ( #1075 )
...
Co-authored-by: Jinzhe Pan <eigensystem1318@gmail.com >
2026-02-10 14:31:36 +08:00
ad58f802f3
[Feat] Port LTX2 trainer ( #1074 )
...
Co-authored-by: Davids048 <jundasu@ucsd.edu >
Co-authored-by: Matthew Noto <99706358+RandNMR73@users.noreply.github.com >
2026-02-09 17:32:57 -08:00
Wei Zhou
04fa356ee3
[Misc] [Training] Fixed a bunch of bugs in current training pipeline ( #1084 )
2026-02-09 16:01:05 -08:00
William Lin
75e193a2c9
[core] Refactor and centralize our registry for models, pipelines, and sampling params ( #1066 )
2026-02-05 14:40:30 -08:00
XOR-op
d6e0a7d0dd
[refactor] Action module ( #1065 )
2026-02-05 13:56:35 -08:00
Mingjia Huo
aae48a7e90
[feat] HYworld VAE with cache ( #1057 )
2026-02-05 04:18:17 -08:00
Shao Duan
d750b463dc
Added Sequence Parallelism for LTX-2 Distilled ( #1036 )
2026-02-04 15:25:30 -08:00
Kaiqin Kong
0c6862ca55
[feature] Add Matrix Game 2.0 training ( #1017 )
...
The CI tests are quite unstable, but since multiple CI tests indicates that each individual tests are passed, I think we can merge this.
2026-01-26 19:21:43 -08:00
Mingjia Huo
59e00f6164
[feat] Add HY-World1.5-Bidirectional-480P-I2V ( #1027 )
...
VAE requires further improvement, will raise PR in near future.
2026-01-23 14:18:04 -08:00
Aryan Kumar