shaoxiongduan
f6275f8005
[feat] Port wm-eval into fastvideo as fastvideo.eval
...
Adds an in-process evaluation suite covering native (SSIM/PSNR/LPIPS/
optical_flow), audio, physics_iq, vbench (16 sub-metrics), and
videoscore2. Public API: create_evaluator/evaluate, BaseMetric +
@register, ensure_checkpoint, get_cache_dir. CLI: fastvideo eval
list/run.
VBench upstream pinned as a git submodule at
fastvideo/third_party/eval/vbench (Vchitect/VBench@45e79ec ); modern-dep
compat is achieved via runtime shims in vbench/__init__.py rather than
on-disk patches. CLIP/torch.hub caches are routed through
${FASTVIDEO_EVAL_CACHE}; HF cache stays at the system default.
ensure_checkpoint delegates to fastvideo.utils.get_lock + huggingface_hub
primitives. Evaluator supports release_cuda_memory(), unload(),
reload() for training-time eval that frees GPU between calls.
Verified parity against upstream vbench (5/8 metrics bit-exact, others
within 1% drift driven by transformers/torch version skew) and against
upstream VideoScore2 (regex anchored on the actual model's output
format, soft-score formula matches upstream's argmax*max_prob/total).
Includes docs/contributing/eval-metrics.md as the porting guide.
Out of scope (deferred follow-ups): MIND, VBench-2.0, FVD as a
registered metric, training-time EvalCallback.
2026-05-01 23:17:19 +00:00
Jinzhe Pan and Darren Sadr
4713fc17ed
[feat] Job Runner UI ( #1189 )
...
Co-authored-by: Darren Sadr <darrensadr@gmail.com >
2026-04-02 16:07:24 -07:00
Jinzhe Pan
c0c8e39c04
Revert "[feat] Job Runner UI" ( #1188 )
2026-03-29 16:46:27 +08:00
Darren
f72618dafb
[feat] Job Runner UI ( #1172 )
2026-03-29 16:17:56 +08:00
alexzms
14261bc98c
[feat] pre-commit support 120 col num ( #1167 )
2026-03-11 20:19:30 -07:00
Ajay Anubolu
e63b7d8ac4
[Feat] Added OpenAI-compatible API server and benchmark script ( #1109 )
2026-03-02 17:12:32 -05:00
Zhang Peiyuan and Will Lin
fc80d95d7e
[Misc] Remove STA ( #1124 )
...
Co-authored-by: Will Lin <wlsaidhi@gmail.com >
2026-02-23 15:14:42 -08:00
Zhang Peiyuan
03d9ce2edb
[Misc] Remove StepVideo ( #1118 )
2026-02-21 17:15:42 -08:00
10fc92dba5
Upstream LTX2 Training ( #1116 )
...
Co-authored-by: RandNMR73 <notomatthew31@gmail.com >
Co-authored-by: JerryZhou54 <zhouw.jerry2017@outlook.com >
Co-authored-by: Davids048 <jundasu@ucsd.edu >
Co-authored-by: Peiyuan Zhang <a1286225768@slurm-h200-204-239.slurm-compute.tenant-slurm.svc.cluster.local >
2026-02-21 16:06:55 -08:00
alexzms
d925ad05f3
[bugfix] fastvideo-kernel: fix VSA Triton padding NaNs and support q/kv length mismatch ( #1094 )
2026-02-13 12:39:49 -08:00
William Lin
88f38eb0f4
[misc] upgrade torch to 2.10 ( #1048 )
2026-02-05 04:15:22 -08:00
William Lin
c5dc244871
[bugfix] add omegaconf as dep. ( #1032 )
2026-01-22 11:59:28 -08:00
alexzms
dbf3917bf4
[fastvideo-kernel] replace map to index with Triton implementation + add vsa benchmark ( #1029 )
2026-01-22 11:35:02 -08:00
Shao Duan and Will Lin
029216029f
Added LTX-2 Distilled T2V Generation ( #1016 )
...
Co-authored-by: Will Lin <wlsaidhi@gmail.com >
2026-01-21 14:11:39 -08:00
alexzms and William Lin
31f44110b5
[kernel] [bugfix] [ci] bump v0.2.4. Fix STA output handling, TurboDiffusion CUDA norm dtypes for fastvideo-kernel unit tests. ( #1020 )
...
Co-authored-by: William Lin <SolitaryThinker@users.noreply.github.com >
2026-01-19 17:42:42 -08:00
William Lin
d58c551c11
[chore] release fastvideo-kernel 0.2.3 ( #1018 )
2026-01-17 02:24:23 -08:00
William Lin
7188170277
[misc] [bugfix] unpin 'av' in pyproject ( #1009 )
2026-01-13 15:40:46 -08:00
William Lin
cf67618cad
[chore] release 0.1.7 (real) ( #980 )
2026-01-05 15:47:05 -06:00
William Lin
8eb3140b2f
[misc] pin fastvideo-kernel in .toml file ( #989 )
2026-01-05 13:42:32 -06:00
William Lin
9cd6a86b95
[chore] release v0.1.7 ( #955 )
2025-12-27 05:05:37 -06:00
alexzms and Shao 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
RoyWang
e0ad145152
[feat] add sliding_tile attention triton kernel and ROCM support ( #916 )
2025-12-22 18:02:51 -06:00
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 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 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
William Lin
1048d79cf8
[bugfix] pin gradio version and set current_vsa_sparsity in TrainingPipeline ( #798 )
2025-09-11 17:04:47 -07:00
William Lin
2dcc5ea4f6
[chore] Release 0.1.6 ( #768 )
2025-08-28 20:56:21 -07:00
William Lin
3ef04f1654
[misc] [docs] Various fixes for logging and docs ( #758 )
2025-08-23 21:13:50 -07:00
William Lin
60f61c8101
[bugfix] fix pyproject install and VSA precision test ( #726 )
2025-08-08 18:45:03 -07:00
Jinzhe Pan
86604a684b
[3/3][Preprocess] add preprocessing workflows ( #645 )
2025-08-07 01:49:07 -07:00
William Lin
0ceff110da
[chore] Release 0.1.5 ( #717 )
2025-08-06 13:07:52 -07:00
Kevin Lin
44da97da92
[chore] Release 0.1.4 ( #667 )
2025-07-30 01:02:36 -07:00
Kevin Lin
d8bb5abc46
[CI] Fix ComfyUI publisher ID ( #648 )
2025-07-25 19:02:52 -07:00
Kevin Lin
cc703eca51
[CI] Add publish workflow for ComfyUI ( #647 )
2025-07-25 18:39:05 -07:00
William Lin
f572319bd9
[Feature] Remove V1 folder ( #642 )
2025-07-24 22:43:12 -07:00
Zhang Peiyuan and root
a37b39d83c
Py/add triton block sparse ( #593 )
...
Co-authored-by: root <a1286225768@gmail,com>
2025-07-17 16:50:40 -07:00
William Lin
576c214f28
[v0] Remove V0 code ( #621 )
2025-07-15 22:05:16 -07:00
RandNMR73
b79d1fc15b
video gen working on apple silicon (addressed issues from prior pr) ( #595 )
2025-07-15 22:04:27 -07:00
William Lin
eb66e1c18d
[chore] release 0.1.2 ( #622 )
2025-07-15 14:42:54 -07:00
Wenxuan Tan
7244a4b27f
[CI] Add LoRA inference tests ( #546 )
2025-07-15 15:06:44 -05:00
William Lin
bf4de1f38f
[chore] Upgrade min Python version from 3.8 to 3.10 ( #597 )
2025-07-04 22:08:31 -05:00
William Lin
66fdcc8e76
[Training] Use inference pipeline for training validation ( #585 )
2025-07-04 17:23:55 -05:00
William Lin
32133171da
[chore] Release 0.1.1 ( #592 )
2025-07-01 01:43:12 -05:00
Kevin Lin
19674c6f29
[CI] Fix fork builds ( #590 )
2025-07-01 01:03:34 -05:00
Kevin Lin
580d6dfe1f
[CI] Add tests to Modal ( #562 )
2025-06-28 14:02:16 -05:00
William Lin
46a0a85d85
[Training] Fixes SP for training; Improve Datasets and schema ( #555 )
2025-06-26 21:13:28 -05:00
William Lin
d41186cb4a
[Feat] Add Stage input and output verification ( #523 )
2025-06-18 23:29:11 -07:00
78e0c7eec9
Specify cu128 Pytorch installation ( #530 )
...
Co-authored-by: Edenzzzz <wtan45@wisc.edu >
Co-authored-by: Wenxuan Tan <wenxuan.tan@wisc.edu >
2025-06-18 20:02:50 -05:00
Kevin Lin
d71a4ebffc
[CI] Update Docker image to flash-attn 2.8.0 / CUDA 12.8 ( #524 )
2025-06-16 17:48:23 -07:00
shaoxiongduan