 Will Lin
|
6b5b2dc6e7
|
mp training
|
2025-05-27 11:38:47 -07:00 |
|
|
Will Lin
|
91b7cc1be8
|
move utils into training_utils
|
2025-05-25 18:23:47 -07:00 |
|
|
Zihang-He
|
d6365373b4
|
added gradient clipping
|
2025-05-25 23:54:10 +00:00 |
|
|
Will Lin
|
50fb94b902
|
gradient checking
|
2025-05-25 15:20:41 -07:00 |
|
|
Will Lin
|
2caa0d4d0b
|
cleanup
|
2025-05-24 17:07:17 -07:00 |
|
|
Will Lin
|
24db823998
|
add validation
|
2025-05-24 16:27:05 -07:00 |
|
|
Will Lin
|
8c4704edf5
|
update train dependecies
|
2025-05-23 12:48:06 -07:00 |
|
|
JerryZhou54
|
dfba7ec833
|
Small fix
|
2025-05-23 19:03:58 +00:00 |
|
|
JerryZhou54
|
7a2e171f1b
|
Small fix
|
2025-05-23 19:01:59 +00:00 |
|
|
JerryZhou54
|
a8aac6090a
|
Integrate the new parquet dataloader into training pipeline
|
2025-05-23 18:27:52 +00:00 |
|
|
|
191d1be3b4
|
Will/training (#425)
Co-authored-by: Kevin Lin <42618777+kevin314@users.noreply.github.com>
Co-authored-by: William Lin <SolitaryThinker@users.noreply.github.com>
Co-authored-by: Will Lin <wlsaidhi@gmail.com>
|
2025-05-23 02:06:54 -04:00 |
|
|
JerryZhou54
|
338ea1e5f2
|
Add script to upload preprocessed dataset to HF
|
2025-05-23 06:05:40 +00:00 |
|
|
JerryZhou54
|
42a2f272d5
|
Preprocessing Stage: 1. Save to parquets periodically 2. Allow resuming from the middle 3. Doesn't support multi-gpu for now. Data Loader Stage: 1. Allow multi-gpu dataloader 2. Doesn't drop files even if number of parquet files is not divisible by num_gpus 3. Able to resume training
|
2025-05-23 00:57:39 +00:00 |
|
|
JerryZhou54
|
982bfcfdc8
|
Fix small issues when loading mask
|
2025-05-21 22:46:32 +00:00 |
|
|
JerryZhou54
|
2ac06379a7
|
Finish data preprocessing and loading
|
2025-05-21 22:34:03 +00:00 |
|
|
JerryZhou54
|
baaa1673f7
|
Add data preprocessing script for WAN
|
2025-05-19 15:09:26 +00:00 |
|
|
William Lin
|
ace6e971e5
|
[V1] Remove vLLM dependency (#413)
|
2025-05-18 00:57:28 -07:00 |
|
|
William Lin
|
b4f6758253
|
[Teacache] allow None for forward_context batch when using teacache (#412)
|
2025-05-17 18:43:14 -07:00 |
|
|
William Lin
|
535d29b392
|
[Docs] Fix image (#407)
|
2025-05-12 14:30:05 -07:00 |
|
|
William Lin
|
b4255517e0
|
[Docs] Add CLI docs (#406)
|
2025-05-12 14:16:48 -07:00 |
|
|
William Lin
|
6eeb60613f
|
Release 0.1.0 (#405)
v0.1.0
|
2025-05-12 11:54:23 -07:00 |
|
|
William Lin
|
53d2c7791f
|
[V1] Update where num_frame rounding is done (#403)
|
2025-05-12 11:52:49 -07:00 |
|
|
William Lin
|
53cb693dca
|
[V1] Docs Update (#402)
|
2025-05-12 11:52:09 -07:00 |
|
|
Kevin Lin
|
6f72d24876
|
[CLI] Default to pipeline config (#401)
|
2025-05-12 00:22:53 -07:00 |
|
|
William Lin
|
d1459e9976
|
[V1] Update README (#400)
|
2025-05-11 22:32:03 -07:00 |
|
|
William Lin
|
59ab481eb1
|
release 0.0.5 (#399)
v0.0.5
|
2025-05-11 16:23:11 -07:00 |
|
|
William Lin
|
0cf001986a
|
[Docs] More docs update (#394)
|
2025-05-11 16:19:47 -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 |
|
|
Kevin Lin
|
4b0970cbbf
|
[CI] Set volume_size required to false (#398)
|
2025-05-11 15:55:34 -07:00 |
|
|
Kevin Lin
|
94bf47a572
|
[CI] Set default disk size (#397)
|
2025-05-11 15:34:17 -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 |
|
|
Kevin Lin
|
fb0581d5b0
|
[CLI] Update cli to support new api/model config (#384)
|
2025-05-11 13:50:33 -07:00 |
|
|
Kevin Lin
|
6c74ab4132
|
[CI] Use python 3.10/3.11 for SSIM test (#392)
|
2025-05-10 13:48:29 -07:00 |
|
|
William Lin
|
9a91021c56
|
[Docs] Add collect_env.py and various docs update (#393)
|
2025-05-10 13:42:42 -07:00 |
|
|
Wei Zhou
|
51c94d6a73
|
[Misc] Small Fixes & Features (#390)
|
2025-05-07 15:40:49 -07:00 |
|
|
William Lin
|
dba38dbc03
|
Release 0.0.4 (#388)
|
2025-05-07 02:40:42 -07:00 |
|
|
William Lin
|
2034cc3c4f
|
[misc] Improve worker cleanup (#387)
|
2025-05-06 22:45:22 -07:00 |
|
|
William Lin
|
c69afce2f6
|
[Docs] Update for V1 (#381)
|
2025-05-06 16:34:44 -07:00 |
|
|
Wei Zhou
|
b08e758eb3
|
Small Fixes & Features (#378)
|
2025-05-06 15:52:34 -07:00 |
|
|
William Lin
|
3f3462d7ce
|
Cleanup Teacache params (#386)
|
2025-05-06 15:52:05 -07:00 |
|
|
William Lin
|
c9c47dd89c
|
Add Teacache to V1 (#371)
|
2025-05-06 11:58:56 -07:00 |
|
|
William Lin
|
9c4ef7c2f1
|
[Lint] fix (#382)
|
2025-05-06 00:42:55 -07:00 |
|
|
Kevin Lin
|
f25eb4b905
|
[CI] Add write permissions to build-image workflow (#379)
|
2025-05-05 19:21:03 -07:00 |
|
|
Kevin Lin
|
048d55ccbb
|
[CI] Add new images for different Python versions (#377)
|
2025-05-05 10:28:33 -07:00 |
|
|
Wei Zhou
|
a271c55fe4
|
Fix FSDP issues when using cpu_offload flag (#376)
|
2025-05-02 15:54:52 -07:00 |
|
|
William Lin
|
f663ae0d8a
|
change gradio example to use model configs (#375)
|
2025-05-02 10:42:03 -07:00 |
|
|
William Lin
|
c0911aa3dd
|
release 0.0.3 (#374)
|
2025-05-02 03:50:41 -07:00 |
|
|
William Lin
|
5f59687ae7
|
Fix model config for python 3.11+ (#373)
|
2025-05-02 03:18:56 -07:00 |
|
|
Wei Zhou
|
5adbc81cdc
|
Refactor encoder (#370)
|
2025-05-02 02:41:12 -07:00 |
|
|
Kevin Lin
|
f26d5c37c1
|
Update SSIM tests to use new API (#369)
|
2025-05-01 04:14:24 -07:00 |
|