SolitaryThinker
e9d95b1c10
wip
2025-12-12 06:30:08 +00:00
SolitaryThinker
8b55e9706c
wip
2025-12-10 01:59:07 +00:00
William Lin
3ff640b2e6
[bigfix] [distillation] Fix DMD inference pipeline noise initialization shape ( #921 )
2025-12-08 13:00:48 -08:00
William Lin
c722429ab5
[docs] fix testing.md visibility ( #920 )
2025-12-08 00:44:53 -08:00
KyleShao and KyleS1016
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 Tan and SolitaryThinker
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
fb6cbf23e6
Fix the docs ( #905 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: William Lin <SolitaryThinker@users.noreply.github.com >
2025-11-27 00:37:03 -08:00
Mihir Jagtap
c8fdd5ed7b
[docs] modified the .github/workflows/docs.yml file to include path filtering ( #906 )
2025-11-26 17:34:21 -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
Zhang Peiyuan
5d1c7852b7
+ Awesome work using FastVideo or our research projects ( #898 )
2025-11-23 22:22:27 -08:00
Wenxuan Tan
77a211d006
[misc] Update wechat link ( #893 )
2025-11-20 19:59:05 -08:00
Wei Zhou
bef8169bb1
[Feat] [I2V] resize all image sizes to below 480*832 ( #890 )
2025-11-20 00:08:36 -08:00
William Lin
681f1583f9
[readme] update link to inference code ( #887 )
2025-11-19 13:24:13 -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
Mihir Jagtap
8c55fdaf7e
[docs] add favicon ( #878 )
2025-11-15 13:44:16 -08:00
Y-aang
c30779184f
fix: incorrect dv in vsa Triton kernel causing test_vsa error ( #879 )
2025-11-14 22:00:39 -08:00
William Lin
9d188c0b6c
[misc] update wechat and slack invite links ( #875 )
2025-11-12 23:03:56 -08:00
Mihir Jagtap
9dd7c54221
[docs] Update Home Readme.md with fixed links ( #873 )
2025-11-12 13:32:44 -08:00
William Lin
62b95d8287
[feat] prepare for wan2.2 SF ( #861 )
2025-11-04 18:06:48 -08:00
Kaiqin Kong
fdf21702f5
[Docs] add diagrams to docs ( #863 )
2025-11-04 16:29:07 -08:00
Ohm-Rishabh
2972fc9449
Improve FSDP loading with size-based filtering ( #853 )
2025-11-04 15:31:07 -08:00
Mihir Jagtap
8f5712629f
[docs] port to mkdocs ( #855 )
2025-11-04 14:31:56 -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 Lin and ainsley
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
William Lin
4f3e8751db
[bugfix] [misc] Use training_state_checkpointing_steps in scripts/ ( #846 )
2025-10-19 20:20:53 -07:00
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
Zhang Peiyuan
2415226d25
Update WeChat Link
2025-10-13 21:02:46 -07:00
Jiali Chen
404314d00f
[Feature]Add video-to-video (V2V) pipeline ( #829 )
2025-10-12 21:53:05 -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
Zhang Peiyuan
9ce7c8039e
Update Wechat link
2025-10-06 15:01:19 -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
William Lin
958ffec844
[bugfix] Update learning rates for sparse distillation recipe ( #812 )
2025-09-22 12:07:03 -07:00
SolitaryThinker