vanch
384eee8aef
feat(mlx): add FastH3-8-Step-V2 DMD schedule and thermal-safe MLX inference
...
- Support official 8-step DMD schedule from fastvideo_inference.json in MLX pipeline
- Implement MiniMaxH3SchedulerState.from_dmd_steps for exact sigma ladder calculation
- Add auto-detection of fastvideo_inference.json in checkpoint converter AdaLN precomputation
- Add inter_step_cooldown_s and per-step MLX graph/cache cleanup to prevent thermal throttling
- Support configurable VAE tile sizes to guarantee 256px tiled decode without grid artifacts
- Skip non-existent shard files gracefully in Qwen3-VL conditioner
2026-09-17 16:12:02 +08:00
Raghav K
9b0e57fe4b
[ci] Make Dreamverse provider race test deterministic ( #1729 )
2026-09-15 14:13:56 -07:00
William Lin
0100218594
[feat] Support the FastH3 8-Step V2 checkpoint: checkpoint-defined shifts, explicit DMD schedule, new example ( #1852 )
2026-09-15 14:13:45 -07:00
li-lizhe
39718cd54d
[bugfix] fix(cosmos): make AdaLayerNorm autocast device-agnostic ( #1818 )
2026-09-15 07:44:51 -07:00
Ishan and SolitaryThinker
37d06a832f
[feat] Add fastvideo serve configs for Wan CUDA models ( #1801 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-09-14 18:23:35 -07:00
sudhirpol522
8839ba8d4d
[bugfix] Add OpenAI-compatible image generation endpoint ( #1840 )
2026-09-14 17:55:56 -07:00
sudhirpol522 and SolitaryThinker
61b91220c0
[bugfix] Validate image response format before generation ( #1841 )
...
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com >
2026-09-14 17:01:40 -07:00
Lele
316f3876c2
[bugfix]: allow MiniMax H3 frame padding at the 15-second limit
...
Accept the causal-VAE-aligned 362-frame bucket (15.083 s) for 15-second H3 requests.
- Hoist MINIMAX_H3_MIN/MAX_ALIGNED_FRAMES next to align_num_frames and reuse them in the CUDA stage, the MLX runtime, and the LoRA example so the bound is consistent across entry points.
- State the accepted frame range in the error messages.
- Cover seconds="15" -> 362 at OpenAI admission and the MLX resolve_geometry bound.
- Update the Spark/openai cookbook frame caps from 345 to 362.
Known gaps: no GPU-lane coverage for the 362 bucket (SSIM runs 124 frames; the golden gate is a fixed-geometry fingerprint), and explicit num_frames=360 still hits the pre-existing grid gate.
2026-09-14 16:54:41 -07:00
Yaegaki1Erika
614b59543c
[bugfix]: respect serialized tensor dtype in parquet dataloader ( #1843 )
2026-09-14 16:34:25 -07:00
William Lin
1c14afd559
[docs]: refresh AGENTS.md maps and add Wan SP/I2V and CI test notes ( #1845 )
2026-09-14 16:06:53 -07:00
Yaegaki1Erika
9a3c45779c
[bugfix]: fix Wan I2V DMD conditioning under sequence parallelism ( #1844 )
...
The pipeline pre-sharded only the image conditioning along the temporal axis while the noise input stayed full-length, so concatenation could not match for sp_world_size > 1. WanTransformer3DModel shards the flattened token sequence after patch embedding, so pass full-length mask+latent conditioning and let the transformer shard.
Also reads temporal_compression_ratio from the VAE config, simplifies the conditioning mask, concatenates in the transformer's (bs, c, t, h, w) layout, and adds unit coverage.
Co-authored-by: Yaegaki1Erika <70182590+Yaegaki1Erika@users.noreply.github.com >
2026-09-14 15:58:13 -07:00
Kyle Hu
bfc9c01797
[feat]: convert the MiniMax H3 text encoder to NVFP4 ( #1838 )
2026-09-12 18:48:07 -07:00
Kyle Hu
3a3ad3d209
[feat]: NVFP4 text encoder for MiniMax H3 ( #1837 )
2026-09-12 18:31:59 -07:00
lpc0220 and Claude Fable 5.1
aef4e9b3b1
[kernel] VSA kernel: one sm_100a / sm_103a image per listed arch; un-gate backward on sm_103a ( #1833 )
...
Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com >
2026-09-12 16:49:36 -07:00
a943220c11
[bugfix]: drop dead h3_sequential_load from Spark FastH3 presets ( #1831 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com >
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-09-08 12:38:06 -07:00
William Lin
556ac7088e
[refactor] Simplify Wan sampling and tests ( #1825 )
2026-09-07 15:57:19 -07:00
Junda Su
e7456f1b75
Add H3 support into Dreamverse ( #1800 )
2026-09-07 13:09:44 -07:00
lpc0220
c993d7393e
[kernel] sm_100a CUDA backward for VSA block-sparse attention (blk64) ( #1819 )
2026-09-06 21:00:18 -07:00
William Lin
7f83164233
[refactor] Move Wan VAE into the Wan package ( #1824 )
2026-09-05 18:43:55 -07:00
Junda Su
4e52f47d1e
[feat] add MXFP8 support on H3 ( #1796 )
2026-09-05 17:08:58 -07:00
William Lin
e19913f6e9
[refactor] Group Wan transformer and config ( #1823 )
2026-09-05 17:05:32 -07:00
William Lin
2413a57651
Disable old SSIM models ( #1820 )
2026-09-04 21:20:48 -07:00
SYLAR
7bb76b5ec9
[feat] Add native SM103a VSA support ( #1812 )
...
Signed-off-by: lishunyang12 <lishunyang12@163.com >
2026-09-03 15:00:28 -07:00
Aryan Kumar and Aryan Kumar
0bd19a976b
[docs]: add one-Spark FastH3 cookbook runtime with a device-count row ( #1811 )
...
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com >
2026-09-02 10:05:59 -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
vanch