Commit Graph
61 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
Zhang Peiyuan 66012d3a4c [Feat][Dataloader] 1/n Refactor parquet map-style dataloader (#492) 2025-06-10 16:00:13 -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
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
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
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
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
applesaucethebunandBrayden Zhong 51956369a5 [Misc] Replace instances of time.time() with time.perf_counter() (#396)
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
2025-05-11 15:56:39 -07:00
River (Zihang He)andWill Lin 1a3ac9074b Zihang stepvideo v1 (#389)
Co-authored-by: Will Lin <wlsaidhi@gmail.com>
2025-05-11 14:41:42 -07:00
William Lin 9aadb4bf8c [1/n] [v1] Add Worker abstractions for User API (#336) 2025-04-18 14:38:46 -07:00
Yongqi Chen 8a73876d3b add STA to Wan v1 (#349) 2025-04-17 16:35:19 -07:00
Zhang PeiyuanandSolitaryThinker 2325adffa2 Add STA to V1 (#312)
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
2025-04-15 02:39:58 -07:00
William Lin 13583f5ffb [Model] Remove RMSNorm's forward_native hardcode from Wan (#339) 2025-04-14 16:46:43 -07:00
William LinandJerryZhou54 008ee2099a V1 wan rebased (#335)
Co-authored-by: JerryZhou54 <zhouw.jerry2017@outlook.com>
2025-04-11 15:34:54 -07:00
William Linandkevin314 c64f826ae2 Add torch sdpa backend to ssim test (#316)
Co-authored-by: kevin314 <kevin.lin.cs1@gmail.com>
2025-04-07 13:50:46 -07:00
1fee098f10 [do not merge] Rebased refactor (#270)
Signed-off-by: <>
Co-authored-by: William Lin <SolitaryThinker@users.noreply.github.com>
Co-authored-by: Will Lin <wlsaidhi@gmail.com>
Co-authored-by: Zhou, Wei <wzhou322@gatech.edu>
Co-authored-by: Kevin Lin <42618777+kevin314@users.noreply.github.com>
Co-authored-by: kevin314 <kevin.lin.cs1@gmail.com>
Co-authored-by: JerryZhou54 <69577934+JerryZhou54@users.noreply.github.com>
Co-authored-by: Yongqi Chen <144848849+BrianChen1129@users.noreply.github.com>
Co-authored-by: Peiyuan Zhang <m2deng@ucsd.edu>
2025-03-29 17:43:47 -05:00
Yongqi ChenandPeiyuan Zhang 1e08893546 Added multi-GPU support for Hunyuan STA (#211)
Co-authored-by: Peiyuan Zhang <a1286225768@gmail.com>
2025-02-21 14:16:28 -08:00
Zhang Peiyuan 09ab452610 Update STA README.md (#206) 2025-02-20 22:26:26 -08:00
ead6c62be4 [Feat] Add STA for StepVideo (#200)
Co-authored-by: rlsu9 <r3su@ucsd.edu>
Co-authored-by: BrianChen1129 <yongqich@umich.edu>
2025-02-20 11:33:58 -08:00
Yongqi ChenandPeiyuan Zhang 76a12cc8a1 Infer sta tea with torch.compile (#190)
Co-authored-by: Peiyuan Zhang <a1286225768@gmail.com>
2025-02-18 11:29:36 -08:00
Yongqi ChenandPeiyuan Zhang 9ea39cee57 Add STA and teacache forward (#184)
Co-authored-by: Peiyuan Zhang <a1286225768@gmail.com>
2025-02-15 16:22:01 -08:00
Brian Chen 218449c54d adding hunyuan hf (support lora finetuning); unified hunyuan hf inference with quantization (#135) 2025-01-13 19:47:42 -08:00
Yuzhou Nieand“Peiyuan Zhang” 4a1f1e35bb add parallel for vae decoding (#134)
Co-authored-by: “Peiyuan Zhang” <a1286225768@gmail.com>
2025-01-07 17:14:21 -08:00
Zhang Peiyuan dd75ee8509 [Fix] Save CK, Dataset bug fix (#125) 2024-12-31 22:19:10 -08:00
rlsu9 0aed1868df [feat]: Add format auto fixer to main branch (#124) 2024-12-31 15:23:17 -08:00
Zhang Peiyuanandrlsu9 88b2583c2c [feat]:Single 4090 inference for fasthunyuan (#104)
Co-authored-by: rlsu9 <r3su@ucsd.edu>
2024-12-25 12:40:16 -08:00
Brian Chen edf116fa46 fix lora checkpoint saving issue (#97) 2024-12-19 08:42:59 -08:00
a57122c519 Rlsu lora readme (#86)
Co-authored-by: rlsu9 <r3su@ucsd.edu>
Co-authored-by: rlsu9 <147024991+rlsu9@users.noreply.github.com>
2024-12-17 11:37:07 -08:00
Zhang Peiyuanandrlsu9 b393570e45 Update README (#85)
Co-authored-by: rlsu9 <r3su@ucsd.edu>
2024-12-16 17:06:14 -08:00
Zhang Peiyuanandrlsu9 285635e8c0 Clean up (#84)
Co-authored-by: rlsu9 <r3su@ucsd.edu>
2024-12-15 20:33:11 -08:00
Zhang Peiyuanandrlsu9 58cfd71b5e Cleanup
Co-authored-by: rlsu9 <r3su@ucsd.edu>
2024-12-15 17:03:29 -08:00
Hangliang Dingandrlsu9 3bf892b6ab update release readme (#81)
Co-authored-by: rlsu9 <r3su@ucsd.edu>
2024-12-15 22:24:13 +08:00
Zhang Peiyuan 85639d1101 [feat] add hunyuan adv (#79) 2024-12-13 11:52:57 -08:00
Zhang Peiyuanandforeverpiano 6ab2263f3a [Feat] Add HunyuanVideo (#78)
Co-authored-by: foreverpiano <pianoqwz@qq.com>
2024-12-12 14:14:09 -08:00
Zhang Peiyuanandrlsu9 b421c2e183 Cleanup (#77)
Co-authored-by: rlsu9 <r3su@ucsd.edu>
2024-12-12 14:04:02 -08:00
Zhang Peiyuan de1e8d868e Cleanup (#75) 2024-12-06 20:56:06 -08:00
Zhang Peiyuanandforeverpiano 8d41d505fe [cleanup] (#72)
Co-authored-by: foreverpiano <pianoqwz@gmail.com>
2024-12-05 21:02:10 -08:00
Zhang Peiyuan cf15594055 [Feat & Debug] fix uncond; multi guidance validaiton; multiphase schedule; linear range (#64)
typo

update

update

typo

[Debug] Typo (#65)

debug gradient accumulation loss

update gitignore

typo

typo

update scripts

update experiment 10

new script

typo

update

update

update

update

wandb offline and dir

runlong

update

update

update

update

update

update

update

fix finetune code bug

update

update

update

add l2

update
2024-11-30 16:43:24 -08:00
Zhang Peiyuan ce95c2df29 [Feat] EMA Distill; Distributed validation (#63)
update
2024-11-29 21:46:40 -08:00
Zhang Peiyuan d417e4c7c4 [Feat] Refactor GAN; State saving & Resume; Experiments script (#59)
typo

add upload command

add

add ema_transform

add ema transformer

remove harcode

ok

ema

remove hardcode

update env

update script; no sp

revert to sp=4, sp bs=2, full shard

add aws efo env

distributed validation

readme

distributed validation

add gupload

linear range; fix uncond; multi guidance validation

add script
2024-11-28 21:09:31 -08:00
Zhang Peiyuanandforeverpiano 7106eadffc [feat]: Add LADD (#45)
Co-authored-by: Peiyuan Zhang <a1286225768@gmail.com>
Co-authored-by: foreverpiano <pianoqwz@gmail.com>
2024-11-15 19:28:41 -08:00
Zhang Peiyuan b042e321a1 [Refactor] Switch to FSDP (#42) 2024-11-09 15:46:25 -08:00