SolitaryThinker
9f28d34d6d
[bugfix]: keep text-encoder CPU offload on by default
...
Revert the default flips from 40c8b7c1 (OffloadConfig.text_encoder and
FastVideoArgs.text_encoder_cpu_offload False -> True). Flipping the
global default changes the baseline VRAM footprint for every model
family, not just Kandinsky, and breaks the unit lane:
fastvideo/tests/api/test_parser.py::test_load_run_config_supports_yaml_roundtrip
still golden-checks text_encoder offload as True.
Nothing in this PR needs the flip: the Kandinsky examples pass
text_encoder_cpu_offload explicitly, and the offload-aware
TextEncodingStage (kept) makes offload work for Kandinsky's CLIP
either way. Offload stays opt-out rather than opt-in.
2026-07-05 15:25:06 -07:00
Will Lin and Claude Fable 5
375ba410c7
[misc]: default text_encoder_cpu_offload to False
...
Keep text encoders GPU-resident by default (both the legacy arg and the
engine-config schema); offload remains an explicit opt-in now that the
swap path makes it work for encoders without FSDP shard conditions.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-07-05 14:58:12 -07:00
William Lin
78d606a3a7
[feat]: make VSA tile cache configurable for training ( #1444 )
2026-06-28 02:18:31 -07:00
6da206e196
[feat] QAD 5090: FP4 QAT linear STE for training (13/12) ( #1463 )
...
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: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-06-18 15:55:47 -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
6392bd40a9
[feat] Dreamverse 10/14: Add serving API contracts ( #1333 )
...
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 >
2026-05-14 10:07:01 -07:00
alexzms
37418946c8
[docs]: clarify real_score_guidance_scale CFG parameterization ( #1256 )
2026-04-26 16:38:00 +08:00
alexzms
14261bc98c
[feat] pre-commit support 120 col num ( #1167 )
2026-03-11 20:19:30 -07:00
Peiyuan Zhang
e1eda47589
remove temporal frame adjustment
2026-02-27 20:47:16 +00:00
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
Zhang Peiyuan
03d9ce2edb
[Misc] Remove StepVideo ( #1118 )
2026-02-21 17:15:42 -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
Hao Zhang
b92219f6a6
more fix and relocate STA arguments to pipeline config ( #1073 )
2026-02-06 13:38:35 -08:00
Wei Zhou
98308db7e0
[Feature] [Hy1.5] Support HY1.5 super-resolution pipeline for 1080p videos ( #1046 )
2026-02-05 16:39:20 -08:00
Shao Duan and Will Lin
029216029f
Added LTX-2 Distilled T2V Generation ( #1016 )
...
Co-authored-by: Will Lin <wlsaidhi@gmail.com >
2026-01-21 14:11:39 -08:00
XOR-op
785d123e36
[feat] Hooks API and layerwise offloading for all DiTs ( #1006 )
2026-01-17 11:22:02 -08:00
XOR-op
b7f69c2c1d
[feat!] Disable FSDP inference by default ( #1001 )
2026-01-13 14:20:05 -08:00
Ohm-Rishabh
d83f45a6a0
Layer offloading ( #966 )
2026-01-03 21:46:00 -08:00
XOR-op
dd91542cd1
[feat] Support text encoder weight override and quantization ( #983 )
2026-01-03 15:33:33 -06:00
alexzms and Shao Duan
8f1e6c3336
Add LongCat T2V (Base, Distillation and Refinement) Support to FastVideo ( #883 )
...
Co-authored-by: Shao Duan <shaoxiongduan@gmail.com >
2025-12-23 01:11:18 -06:00
William Lin
7f71994653
[misc] Allow manual override of Pipeline class through override_pipeline_cls_name ( #945 )
2025-12-20 14:39:17 -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
Ohm-Rishabh
01c94ef385
[feat] unified trainer logging ( #841 )
2025-10-16 23:16:16 -07:00
William Lin
e1e25e95f9
[feature] Add torch profiler ( #827 )
2025-10-06 07:59:46 -07:00
William Lin
490bde90e1
[bugfix] Allow overriding dit checkpoint for inference and Lower VSA LR in example scripts ( #831 )
2025-10-05 01:44:49 -07:00
dc7596b973
[self-forcing][8/n] Self-Forcing For Wan2.2-A14B + torch.compile training and distillation support ( #818 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-10-02 15:01:45 -07:00
William Lin
335afa4457
[bugfix] Use training_state_checkpointing_steps instead of checkpointing_steps ( #821 )
2025-09-28 15:22:43 -07:00
William Lin
404cbf4f3c
[self-forcing] [6/n] Add Ode Init training ( #811 )
2025-09-22 17:58:19 -07:00
31f000d1cc
[self-forcing] [5/n] Add Self-Forcing distillation pipeline ( #808 )
...
Co-authored-by: RandNMR73 <notomatthew31@gmail.com >
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-09-20 19:32:10 -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
Wei Zhou and SolitaryThinker
c41305ad18
[Feat] Add Wan2.2 14B MoE ( #688 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-08-06 20:31:03 -07:00
Yongqi Chen
c718e56b0d
[Feature] Remove unused args ( #695 )
2025-08-03 23:01:54 -04:00
Yongqi Chen and SolitaryThinker
b65f0316d1
[Feature] Add Wan2.2 DMD example files; Update lr scheduler ( #694 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-08-03 22:55:01 -04:00
Yongqi Chen and SolitaryThinker
5f42748ed1
[Feature] Add Wan2.2-TI2V-5B Sparse Distill ( #690 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2025-08-03 01:29:57 -04:00
Wenxuan Tan
6c81befc87
[Feature] Optionally enable torch compile ( #684 )
2025-08-01 20:17:40 -07:00
Yongqi Chen
9185978c55
[Bugfix] Fix multi-gpu training lr_scheduler ( #682 )
2025-08-01 15:54:03 -04:00
Yongqi Chen
4cb046768d
[Feature]Add DMD distillation training resume checkpoint; Update DMD CI test ( #662 )
2025-07-29 19:06:05 -04:00
Jinzhe Pan
7b6c8aee99
[2/3][Preprocess] refactor pipeline registry & file structure ( #639 )
2025-07-27 23:30:17 -07:00
Yongqi Chen
636524e87f
[Feature] Add Wan-14B-T2V-VSA CLI inference; add master port args ( #653 )
2025-07-27 07:13:44 -04:00
Yongqi Chen
247fe273d8
[Feature] Add DMD T2V training pipeline ( #651 )
2025-07-27 03:35:51 -04:00
William Lin
81c9df629c
[core] Add offloading for vae and image encoder and rename offloading args ( #643 )
2025-07-25 17:55:03 -07:00
Yongqi Chen
d3c0c52208
[Feature] Add prompt_txt support for CLI inference; Add DMD CLI inference ( #646 )
2025-07-25 19:44:10 -04:00
Jinzhe Pan
3a38f7dfdc
[1/3][Preprocess] refactor preprocessing configs ( #638 )
2025-07-25 14:27:12 -07:00
William Lin
f572319bd9
[Feature] Remove V1 folder ( #642 )
2025-07-24 22:43:12 -07:00
SolitaryThinker