 Shreejith SGandWilliam Lin
|
f8bfc76015
|
feat: consolidate attention kernels into unified fastvideo-kernel package (#946)
Co-authored-by: William Lin <SolitaryThinker@users.noreply.github.com>
|
2025-12-24 01:39:51 -06:00 |
|
|
alexzmsandShao 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
|
8e7d2e7879
|
[bugfix] [dmd2] allow dmd2 simulate_student_forward to use text-only dataset (#951)
|
2025-12-23 00:41:31 -06:00 |
|
|
RoyWang
|
e0ad145152
|
[feat] add sliding_tile attention triton kernel and ROCM support (#916)
|
2025-12-22 18:02:51 -06:00 |
|
|
Wei Zhou
|
1f70032af5
|
[New Model] Hunyuan1.5 (#943)
|
2025-12-21 00:57:52 -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 |
|
|
Loay Rashid
|
2bb3349da1
|
[bugfix] Added VSA Padding logic (#944)
|
2025-12-20 14:29:11 -06:00 |
|
|
Kaiqin Kong
|
8fe1689968
|
[feat] Add Matrix-Game 2.0 (#938)
|
2025-12-20 14:09:12 -06:00 |
|
|
Loay Rashid
|
e53730f324
|
[docs] Minor Fixes (#942)
|
2025-12-19 16:48:16 -06:00 |
|
|
Loay Rashid
|
7a4fe9086a
|
[feat] Support sequence packing and shard after pachification for USP (#894)
|
2025-12-19 16:19:46 -06:00 |
|
|
Ohm-Rishabh
|
d277361aae
|
[misc] add schedule configurations to pytorch profiler (#934)
|
2025-12-18 01:45:23 -06:00 |
|
|
alexzms
|
734a54e7a9
|
[ci]: Use pre-built docker image & skip VSA compilation (#939)
|
2025-12-16 23:14:11 -08:00 |
|
|
alexzms
|
91364982df
|
[Feature] Support for Variable Q/KV Sequence Lengths in VSA ThunderKittens kernel (#911)
|
2025-12-16 20:08:15 -08:00 |
|
|
William Lin
|
50145e4fcb
|
[CI] Fix CI tests (#935)
|
2025-12-16 04:59:43 -08:00 |
|
|
William Lin
|
4112507e99
|
[misc] upgrade pytorch version to 2.9.0 (#928)
|
2025-12-15 04:12:43 -08:00 |
|
|
William Lin
|
424fc2b4ae
|
[bugfix] [lora] [distillation] Fix lora distillation bug (#933)
|
2025-12-15 04:12:02 -08:00 |
|
|
William Lin
|
e6066223e6
|
[bugfix] [VSA] [distillation] Various bugfixes for VSA and distillation and nightly tests (#932)
|
2025-12-12 16:51:54 -08:00 |
|
|
Shreejith SG
|
92fb660c2e
|
Add LoRA extraction, verification, and comparison scripts (#865)
|
2025-12-08 16:07:58 -08:00 |
|
|
William Lin
|
3ff640b2e6
|
[bigfix] [distillation] Fix DMD inference pipeline noise initialization shape (#921)
|
2025-12-08 13:00:48 -08:00 |
|
|
KyleShaoandKyleS1016
|
e04a192de6
|
[feat]: add COSMOS 2.5 DiT implementation (#897)
Co-authored-by: KyleS1016 <kyle.s@gmicloud.ai>
|
2025-12-07 21:48:32 -08:00 |
|
|
William Lin
|
c9ca6d1298
|
[docs] add docs for ssim testing (#918)
|
2025-12-06 18:20:04 -08:00 |
|
|
Wenxuan TanandSolitaryThinker
|
754292c419
|
Use assert_close in tests (#429)
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
|
2025-12-06 18:18:25 -08:00 |
|
|
Qi Jia
|
0082bc66fc
|
fix: correct mp backend GPU assignment on multi-GPU systems (#912)
|
2025-11-30 23:00:22 -08:00 |
|
|
Ohm-Rishabh
|
8b1937422e
|
[feat] training mfu calculation scripts (#871)
|
2025-11-27 16:54:17 -08:00 |
|
|
Loay Rashid
|
1c19a6a00c
|
[Bugfix] Minor bugfixes (#889)
|
2025-11-26 17:20:45 -08:00 |
|
|
William Lin
|
d44409c704
|
[CI] fix VSA training CI (#900)
|
2025-11-24 17:47:59 -08:00 |
|
|
Wei Zhou
|
bef8169bb1
|
[Feat] [I2V] resize all image sizes to below 480*832 (#890)
|
2025-11-20 00:08:36 -08:00 |
|
|
|
e3b4564d5a
|
[feat] Add inference for MoE SF (#880)
Co-authored-by: RandNMR73 <notomatthew31@gmail.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
|
2025-11-19 13:16:24 -08:00 |
|
|
Shao Duan
|
c0d03fc43d
|
[bugfix] [lora] [CI] Fix LoRA alpha scaling factor & Fix LoRA Inference CI (#870)
|
2025-11-19 01:02:01 -08:00 |
|
|
Wei Zhou
|
404ee8538e
|
[Bugfix] [DMD Distillation] Each rank should have its own timestep sampled (#885)
|
2025-11-18 14:03:25 -08:00 |
|
|
Shao Duan
|
e57ac59462
|
Fix mp worker busy loop to handle all string RPC methods (#881)
|
2025-11-16 13:26:44 -08:00 |
|
|
William Lin
|
62b95d8287
|
[feat] prepare for wan2.2 SF (#861)
|
2025-11-04 18:06:48 -08:00 |
|
|
Ohm-Rishabh
|
2972fc9449
|
Improve FSDP loading with size-based filtering (#853)
|
2025-11-04 15:31:07 -08:00 |
|
|
Kevin Lin
|
436c701b9f
|
[bugfix] Add Cosmos2 sampling params to registry (#862)
|
2025-11-02 00:09:17 -07:00 |
|
|
Kevin Lin
|
543fea88e3
|
[Feature] Add Cosmos2 i2v pipeline (#837)
|
2025-10-30 20:03:57 -07:00 |
|
|
Kaiqin Kong
|
bdec816b31
|
move STA_configuration.py to fastvideo/attention/backends (#856)
|
2025-10-29 13:54:13 -07:00 |
|
|
William Lin
|
2cd2e57d2e
|
[ci] fix causal ssim test (#848)
|
2025-10-26 19:33:07 -07:00 |
|
|
William Linandainsley
|
9370234294
|
[feat] Add gradio local inference demo (#847)
Co-authored-by: ainsley <jzhang2765@wisc.edu>
|
2025-10-26 07:01:33 -07:00 |
|
|
Jinzhe Pan
|
50da62e722
|
[bugfix] always force spawn instead of fork (#852)
|
2025-10-23 16:36:50 -07:00 |
|
|
Jinzhe PanandXingyu 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 |
|
|
Jiali Chen
|
404314d00f
|
[Feature]Add video-to-video (V2V) pipeline (#829)
|
2025-10-12 21:53:05 -07:00 |
|
|
zyang6andkiritorl
|
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 |
|
|
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 |
|
|
Yongqi Chen
|
3f77a6805a
|
[Feature]Update count trainable param for FSDP2 (#820)
|
2025-09-28 15:22:04 -07:00 |
|
|
RandNMR73
|
13d0aae706
|
Add Sage Attention 3 Backend (#815)
|
2025-09-24 15:11:38 -07:00 |
|
|
William Lin
|
404cbf4f3c
|
[self-forcing] [6/n] Add Ode Init training (#811)
|
2025-09-22 17:58:19 -07:00 |
|