Commit Graph
216 Commits
Author SHA1 Message Date
William Lin c0026ca5ba [CI] [Training] Initial e2e small training test (#504) 2025-06-11 13:53:36 -07:00
Zhang Peiyuan 0f2bbe71ac [misc] rename dp_size to hdsp_replicate_dim (#491) 2025-06-10 16:36:56 -07:00
Yongqi ChenandJerryZhou54 2a46902ecb [Feature][VSA]Update STA publish workflow (#498)
Co-authored-by: JerryZhou54 <zhouw.jerry2017@outlook.com>
2025-06-10 19:33:34 -04:00
Zhang Peiyuan 66012d3a4c [Feat][Dataloader] 1/n Refactor parquet map-style dataloader (#492) 2025-06-10 16:00:13 -07:00
William Lin f666b9de41 [misc] Add missing license headers (#499) 2025-06-10 14:25:32 -07:00
Yongqi Chen 7e3c073b55 [Feature] Adding VSA inference (#478) 2025-06-10 16:03:53 -04:00
Wei Zhou a6aa21bd07 [bugfix][Cli Inference] Resolve runtime errors when running fastvideo generate (#495) 2025-06-10 02:50:21 -04:00
Wenxuan Tan 6519b57aab [chore] Fix main pre-commit CI failure (#494) 2025-06-10 00:54:37 -05:00
Wei Zhou 675aea6ece [bugfix][Cli Inference] Resolve runtime errors when running fastvideo generate (#493) 2025-06-09 19:49:34 -07:00
Zhang Peiyuan 46e7a15e0d [misc] Improve distributed related env variables and setup (#487) 2025-06-08 09:14:48 -07:00
Yongqi ChenandJerryZhou54 e4f702d7ec [Bug] Fix multi gpus issues in v1 scripts (#489)
Co-authored-by: JerryZhou54 <zhouw.jerry2017@outlook.com>
2025-06-07 21:55:49 -07:00
Wenxuan Tan bb68fcc809 Revert "Add torch.compile for all small ops" (#484) 2025-06-07 07:21:17 -05:00
Wenxuan Tan b392e6a874 Add torch.compile for all small ops (#432) 2025-06-06 21:10:42 -07:00
Zhang PeiyuanandWill Lin 0991003905 [bugfix] [misc] fix denoising stage init; rename distributed env function; fix logging. (#481)
Co-authored-by: Will Lin <wlsaidhi@gmail.com>
2025-06-06 20:01:10 -07:00
Zhang PeiyuanandWill Lin 8f8ce6d9e1 [bugfix] [training] Add negative prompt to preprocessing and validation (#479)
Co-authored-by: Will Lin <wlsaidhi@gmail.com>
2025-06-06 11:21:21 -07:00
KevinzzandBrianChen1129 e3d0cbe185 [STA] Implement mask search for V1's Wan2.1 (#415)
Co-authored-by: BrianChen1129 <yongqich@umich.edu>
2025-06-05 15:03:31 -04:00
eeecho d5ec468d43 [V0] [Distill] support distill in V0 for wan (#444) 2025-06-04 16:20:14 -07:00
Yongqi Chen e55fa6e5dc [Preprocess] I2V dataset (#473) 2025-06-04 16:19:20 -07:00
Wenxuan Tan 61b6ddeee1 [Issue template] Move env report to the end for readability (#476) 2025-06-04 16:18:22 -07:00
William Lin a9a000f45d [bugfix] fix bz >1 for training (#477) 2025-06-04 16:03:39 -07:00
Wenxuan Tan 66b8b8561e [LoRA] Support V1 LoRA inference (#451) 2025-06-04 16:19:29 -05:00
Wenxuan Tan 6684872616 [misc] Find unused port in distributed init (#475) 2025-06-04 14:15:12 -05:00
Wenxuan Tan 7f654e3332 [misc] Polish V1 training code (#469) 2025-06-03 22:02:03 -05:00
William Lin 8631c1b806 [Training] Support Multi-Node training with FSDP + SP (#459) 2025-06-03 17:40:22 -07:00
Wei Zhouand“BrianChen1129” 5357e12b5a Update v1 inference scripts (#467)
Co-authored-by: “BrianChen1129” <yongqich@umich.edu>
2025-06-03 02:54:12 -04:00
Kevin Lin bdfdf1dfee [Training] Add distributed checkpointing (#458) 2025-06-02 15:15:45 -07:00
Wei Zhou d156461785 Fix WanVideo (#461) 2025-06-01 23:08:11 -07:00
Yongqi Chen 6edf113838 [Misc] Bring back mask files under asset/ and update new Wan mask strategy file (#462) 2025-06-01 19:46:11 -07:00
William Lin dcf7738cbc [Misc] disable cast_forward_inputs (#460) 2025-05-31 22:06:29 -07:00
Wenxuan Tan b2ebaaf865 [Misc] Remove InferenceEngine (#455) 2025-05-31 11:12:05 -07:00
Wenxuan Tan 7768bb80f6 misc: add remote pdb for debugging workers (#456) 2025-05-30 20:44:27 -05:00
William Lin a335811869 [Training] [8/n] SP Training (#450) 2025-05-29 17:02:26 -07:00
William LinandZihang-He 357b0533fe [Training] [7/n] gradient clipping (#449)
Co-authored-by: Zihang-He <z6he@ucsd.edu>
2025-05-29 15:07:29 -07:00
William Lin 2ec3732758 [Training] [6/n]Mixed precision training (#448) 2025-05-29 14:34:28 -07:00
Wei Zhouand“BrianChen1129” a004408a93 [Training] [0/n] Add preprocessing pipeline (#442)
Co-authored-by: “BrianChen1129” <yongqich@umich.edu>
2025-05-29 14:30:09 -07:00
007e237e69 [Training] [5/n] Add single gpu training pipeline (#447)
Co-authored-by: JerryZhou54 <zhouw.jerry2017@outlook.com>
Co-authored-by: Wei Zhou <69577934+JerryZhou54@users.noreply.github.com>
Co-authored-by: Kevin Lin <42618777+kevin314@users.noreply.github.com>
Co-authored-by: “BrianChen1129” <yongqich@umich.edu>
2025-05-29 11:49:46 -07:00
Yongqi Chen 8e18dc9f71 Update STA mask strategy downloading (#445) 2025-05-28 12:49:22 -07:00
7ab32539af [Training] [1/n] Add latent datasets (#438)
Co-authored-by: Wei Zhou <wzhou322@gatech.edu>
Co-authored-by: JerryZhou54 <zhouw.jerry2017@outlook.com>
Co-authored-by: “BrianChen1129” <yongqich@umich.edu>
2025-05-28 11:01:52 -07:00
William Lin 6ef8fcb61d [Training] [4/n] add training save checkpoint (#441) 2025-05-27 17:53:53 -07:00
William Lin 016e24da63 [Training] [3/n] Add training args and dependencies (#440) 2025-05-27 17:53:39 -07:00
William Lin 85b8717545 [Training] [2/n] add bwd for all2all and all_gather (#439) 2025-05-27 14:27:54 -07:00
Wenxuan Tan 657fd745e1 misc: Trigger transformers CI for layers and attention code change (#434) 2025-05-27 11:43:23 -07:00
applesaucethebunandBrayden Zhong 12647457a7 [Misc] Small fixes to Torch code (#395)
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
2025-05-23 14:40:24 -07:00
Kevin Lin 298f74f956 Set device for encode (#420) 2025-05-23 14:19:45 -07:00
Wenxuan Tan ee8babb298 Unify env report script in issue template (#423) 2025-05-23 14:19:18 -07:00
Wenxuan Tan 60295cc03f Use version.py (#424) 2025-05-23 14:17:33 -07:00
William Lin 1572e13b6e [Tests] don't run 3.10 and 3.11 for SSIM (#427) 2025-05-23 12:59:50 -07:00
Wenxuan Tan a157275b4c Fix version number (#422) 2025-05-22 12:37:34 -07:00
William Lin c4dbe7dac3 [bug] fix bs > 1 (#418) 2025-05-21 21:07:01 -07:00
Kevin Lin d39591108e Fulfill worker response on interrupt (#417) 2025-05-21 20:59:11 -07:00