H1yori233
5c37eaa60f
[bugfix]: guard automatic FA3 regional compile
2026-09-01 19:40:22 -07:00
Will Lin and Claude Fable 5
8775bff28a
[bugfix] review fixes for regional compile: mode conflict, legacy scoping, AC-prefix loader trap, FA3 guard + config
...
1. mode/options conflict: _compile_model_regions now rejects
torch_compile_kwargs['mode'] with an actionable error instead of letting
torch raise about an 'options' key the user never wrote (the CLI help's
own example uses mode). CLI help updated.
2. Legacy stack scoping: new regional_compile flag (FastVideoArgs, default
False). The modular fastvideo/train moduleloader opts in; legacy
--enable-torch-compile recipes keep their pre-PR whole-model
torch.compile semantics (partial graphs, kwargs passed through).
3. AC-prefix normalization in the weight loader: checkpoint_wrapper strips
its prefix from state_dict() keys but not named_parameters()/
named_buffers(); with pre_fsdp_transform applying AC before load, a
loaded buffer inside a wrapped block was silently converted into a
TRAINABLE parameter by load_state_dict(assign=True) (verified on torch
2.12). All name-keyed lookups (buffer membership, fused weight_loader,
_get_parameter_dtype at load and shard time) now compare canonical names
via _strip_checkpoint_wrapper_prefix.
4. FA3: flash-attn 3's grad-enabled attention path graph-breaks, which
fullgraph regional compile turns into a hard error at step 1 on Hopper
hosts. The loader now detects FLASH_ATTN+fa3 and warns-and-disables
compile instead of crashing, and dmd2_t2v_fa3.yaml ships the recipe with
compile explicitly off (main config annotated).
Tests: mode-conflict rejection; AC-prefix canonicalization incl. the
buffer-stays-buffer regression under assign=True.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com >
2026-09-01 18:08:18 -07:00
Peiyuan
74003332b3
default add compile
2026-09-01 18:04:56 -07:00
root
792ef0d194
[bugfix]: fix compiled Wan modulation gradients
2026-09-01 18:04:56 -07:00
root
1530e4a1ca
[perf]: add safe regional compile for modular training
2026-09-01 18:04:56 -07:00
William Lin
40b93784d2
[docs]: add cookbook link to README ( #1810 )
2026-09-01 12:42:19 -07:00
Aryan Kumar
33d3478bad
[docs] Announce local FastH3 support ( #1809 )
2026-09-01 12:28:04 -07:00
3d8ac9d14b
[feat]: collapse cookbook recipe pages into an accordion layout, add … ( #1805 )
...
Co-authored-by: Vaish, Ishan <isvaish@UCSD.EDU >
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com >
2026-09-01 01:51:51 -07:00
aaef49bfc6
[feat]: run FastH3 across two DGX Sparks with Ray sequence parallel ( #1803 )
...
Co-authored-by: Kyle <shh075@ucsd.edu >
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com >
Co-authored-by: Satyam Srivastava <srivastavasatyam53@gmail.com >
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-09-01 01:37:23 -07:00
Aryan Kumar and Aryan Kumar
cf6a00b9be
[feat]: add opt-in CUDA TAEH3 preview decode for FastH3 ( #1795 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-08-31 23:34:56 -07:00
Shahrad Zomorrodi and Shahrad Zomorrodi
1ae39562dd
[bugfix] Write generated documentation as UTF-8 ( #1797 )
...
Co-authored-by: Shahrad Zomorrodi <264690209+shahradzomorrodi@users.noreply.github.com >
2026-08-31 22:45:03 -07:00
Aryan Kumar and Aryan Kumar
26064193e2
[feat] Add an H3 server cookbook and prompt playground ( #1798 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-08-31 22:14:33 -07:00
William Lin
8446fc003e
[docs]: add FastH3 Preview v1 news links ( #1804 )
2026-08-31 22:12:02 -07:00
Aryan Kumar and Aryan Kumar
a28f2bab4b
[feat] Add an optional MLX TAEH3 preview decoder ( #1794 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-08-31 05:08:06 -07:00
Aryan Kumar and Aryan Kumar
f82d8be4bf
[perf] Sequential MiniMax H3 start with GPU-direct DiT load ( #1793 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-08-31 04:20:21 -07:00
Aryan Kumar and Aryan Kumar
8e1775183e
[perf] Speed up exact MiniMax H3 MLX inference ( #1792 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-08-31 04:14:55 -07:00
Aryan Kumar and Aryan Kumar
620bc36dc4
[docs]: Cookbook catalog improvements ( #1790 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-08-30 17:50:57 -07:00
Suhaan Khurana
29ff16ec96
[feat] Add MiniMax H3 MLX spatial fast mode ( #1789 )
2026-08-30 17:47:02 -07:00
Aryan Kumar and Aryan Kumar
8f9d76a80d
[perf]: dispatch wide-M affine H3 MLX linears through dequant plus dense GEMM ( #1788 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-08-30 14:42:01 -07:00
a4d9a75e2c
[perf] Add MiniMax H3 MLX VSA and SIMD attention ( #1776 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2026-08-30 13:44:54 -07:00
KyleNeverGivesUp
b2db0c0a13
[ci]: seed stable GB10 grad-norm references ( #1756 )
2026-08-30 03:09:18 -07:00
Kevin Lin
6aa7d8a278
[misc] FastVideo Studio UI Additions (H3 Ref2V support) ( #1783 )
2026-08-30 03:06:47 -07:00
Aryan Kumar and Aryan Kumar
ccc9014430
[docs] Add model-family inference cookbook ( #1787 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-08-30 02:26:10 -07:00
William Lin
a159b63c67
[bugfix] Harden OpenAI serving after post-merge review ( #1782 )
2026-08-28 22:29:24 -07:00
ac48bb3cd1
[feat] Add MiniMax H3 MLX T2VA inference ( #1770 )
...
Co-authored-by: Aryan Kumar <aryank@Aryans-Mac-Studio.local >
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: CodeRabbit <noreply@coderabbit.ai >
2026-08-28 12:54:33 -07:00
William Lin
3987b9ddcd
[feat] Align multimodal OpenAI serving APIs ( #1781 )
2026-08-28 10:09:58 -07:00
William Lin
c7da2f5d60
[chore]: release v0.2.1 ( #1778 )
2026-08-28 02:03:18 -07:00
William Lin
39ae1decc0
[misc] pin fastvideo-kernel to exact 0.3.5 ( #1777 )
2026-08-28 02:02:27 -07:00
William Lin
1aed667377
[chore] release fastvideo-kernel 0.3.5 ( #1775 )
2026-08-27 23:18:59 -07:00
William Lin
c1612ff397
[bugfix]: pin fastvideo-kernel to Torch 2.12.0 ( #1774 )
2026-08-27 23:13:54 -07:00
William Lin and shaoxiongduan
a534ba20a0
[feat] Add MiniMax H3 LoRA inference and preview launchers ( #1771 )
...
Co-authored-by: shaoxiongduan <shaoxiongduan@gmail.com >
2026-08-27 14:43:39 -07:00
KyleNeverGivesUp
e9bbaca07d
[perf] Disable every offload path on unified memory, unblocking MiniMax H3 generation on one GB10 ( #1715 )
2026-08-26 15:32:56 -07:00
KyleNeverGivesUp
9bfa585448
[perf]: stop holding the whole checkpoint during DiT load, unblocking MiniMax H3 on one GB10 ( #1714 )
2026-08-26 15:23:51 -07:00
Raghav K
b2062556a9
[perf] VSA Triton: widen the autotune num_stages range (the optimum was outside it) ( #1706 )
2026-08-26 12:30:56 -07:00
KyleNeverGivesUp
c9c5585758
[perf]: MiniMax H3 on GB10 - skip text encoder CPU offload on unified memory (5m49s to 30ms) ( #1710 )
2026-08-26 12:03:14 -07:00
William Lin
9212f4f218
[ci] make GPU validation change-aware ( #1747 )
2026-08-25 21:26:25 -07:00
Aryan Kumar and Aryan Kumar
6388db815b
[bugfix] FastMetal-QAD MLX support: refuse CUDA QAD trees, use packed mlx_dit config, stream loads ( #1736 ) ( #1758 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-08-25 14:51:40 -07:00
lpc0220
7a4285189f
[kernel] Route block-sparse VSA to the sm_100a forward behind FASTVIDEO_VSA_SM100A (opt-in) ( #1754 )
2026-08-24 15:26:56 -07:00
William Lin
a837fe841a
[docs] Update FastH3 README ( #1749 )
2026-08-23 05:05:58 -07:00
William Lin
f9e3680f11
[perf] Align FastH3 optimized inference profile ( #1748 )
2026-08-23 02:01:03 -07:00
William Lin
98f761ec45
[bugfix] validation: inherit the trained denoising ladder ( #1738 )
2026-08-22 23:09:26 -07:00
Shao Duan
c041318f2c
[perf] Add fused NVLink all-to-all for Ulysses ( #1740 )
2026-08-22 23:06:24 -07:00
William Lin
604e0205a4
[perf] Keep odd MiniMax-H3 VSA tiles on sm100a ( #1745 )
2026-08-22 18:29:30 -07:00
William Lin
13213395b4
[perf] Parallelize MiniMax-H3 VAE over sequence ranks ( #1744 )
2026-08-22 18:05:31 -07:00
William Lin
46afee5998
[bugfix] Classify MiniMax-H3 inference controls in schema inventory ( #1743 )
2026-08-22 17:17:02 -07:00
William Lin
c488fa1211
[perf] Add opt-in packed-varlen FA4 for MiniMax-H3 ( #1742 )
2026-08-22 17:16:47 -07:00
William Lin
d3cff517cd
[perf] Add opt-in regional fullgraph compile for DiT inference ( #1741 )
2026-08-22 12:14:39 -07:00
Junda Su
2f3d407406
[perf] Optimize MiniMax H3 VAE decoding ( #1734 )
2026-08-21 14:57:32 -07:00
Kaiqin Kong
bcffa4026e
[perf] Optimize MiniMax-H3 text encoder memory ( #1732 )
2026-08-21 14:57:06 -07:00
William Lin
6d6a10be7a
[feat] FastVideo-Minimax-FastH3-Preview few-step example + 64-token-tile VSA-H3 inference path ( #1731 )
2026-08-21 12:40:09 -05:00
H1yori233