nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,115 Commits 335 Branches 8 Tags
3907a69727af6aab846bb68014e9da2a62c77b1a
Commit Graph
251 Commits
Author SHA1 Message Date
Zhang PeiyuanandClaude Opus 5.5 c520878fd2 [perf]: QAT/QAD add safe regional compile for modular training (#1718) 
Adds opt-in regional torch.compile to the YAML-driven modular Wan trainer (training.model.enable_torch_compile / torch_compile_kwargs) with FA4 and Wan modulation forward/backward as opaque custom ops, compiled repeated DiT blocks after FSDP setup, and activation checkpointing applied before FSDP for trainable Wan transformers.

Merged with main's #1716 (WanModel resolves the checkpointing type in __init__; the PR's pre-FSDP wrap uses it and the post-load wrap is gone) and #1757 (pre_fsdp_model_transform runs before this PR's pre_fsdp_transform). Maintainer review (Swarm order #776): AdaLN skip names are canonicalized through checkpoint-wrapper prefixes, test_inference_regional_compile.py joins the unit lane, the Wan modulation custom-op test moved to the transformer lane, regional_compile is classified in the schema inventory, and a 1/2-GPU training smoke covers fully_shard(CheckpointWrapper) in eager and regional-compile modes. Validated on GB200: the FA4 CuTe forward/backward parity and fullgraph-backward tests and all four smoke cases pass.

Also exempts MMAudio recipes, whose student builds its pipeline config at init, from the fine-tuning recipe construction check that #1648 left failing on main.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 05:24:24 -07:00
Shao DuanSolitaryThinkerClaude Opus 5.5
 		99f8f3e7a7 [feat] Add streaming and GPU-accelerated LoRA extraction (#1784) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 04:48:35 -07:00
William LinWill LinWilliam LinClaude Opus 5.5
 		8530fdc550 [feat] Add external-launcher executor for multi-node inference (#1746) 
Co-authored-by: Will Lin <willlin@nvidia.com>
Co-authored-by: William Lin <8941107+SolitaryThinker@users.noreply.github.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 04:46:26 -07:00
Raghav KandClaude Opus 5.5 315b25d26d [new-model] Add Cosmos Predict2.5 distilled T2W and DFD V2W inference (#1767) 
Adds the Cosmos Predict 2.5 distilled text-to-world sampler (sCM, per-frame timesteps) and the DFD video-to-world pipeline, with their schedulers, registry entries, presets and examples.

Maintainer review fixes (Swarm orders #718 and #748): the DiT receives one shared fps value (its RoPE table is batch-independent, so per-sample vectors crashed batch > 1; differing values now raise), non-finite rollouts raise FloatingPointError instead of being zeroed by nan_to_num, the DFD detector matches "dfd" only in the last path component, the distilled example defaults to 24 fps, and the distilled rollout keeps its state in FP64 through the scheduler step as the official driver does.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 04:42:44 -07:00
Achintya RaiClaude Opus 4.8SolitaryThinker
 		b8920ba50a [misc]: add env var to control process-aware logging (#1680) 
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-10-07 04:31:52 -07:00
Kun LinandClaude Opus 5.5 7320d9d350 [feat] Add HunyuanVideo 1.5 embedding preprocessing pipeline (#1663) 
Adds preprocess_hunyuan15_overfit.py, which writes VAE latents plus Qwen and ByT5 text embeddings in the dual-text parquet schema (pyarrow_schema_t2v_dual_text) that main's HunyuanVideo 1.5 training (#1662) reads; main's guide and overfit config pointed at this script, but nothing in-tree produced text_embedding_2 before.

Reconciled with #1662 during maintainer review (Swarm orders #723 and #777): main's schema and collate are the base. On top of them, both text streams now share one CFG-dropout decision per row also when _sample_index is absent, and a row missing the primary text_embedding raises instead of training unconditioned. The PR's widening of the shared t2v schema and its writer changes were dropped. docs/training/hunyuan15_overfit.md now describes the in-tree script.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 04:20:58 -07:00
Suhaan KhuranaSuhaanCommitsClaude Fable 5SolitaryThinker
 		af78c759f1 [new-model] Add Wan2.2-Animate-14B character animation/replacement inference (#1765) 
Co-authored-by: SuhaanCommits <suhaan@cedar.build>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-10-07 04:19:37 -07:00
Raghav KSolitaryThinkerClaude Opus 5.5
 		f82c190cbb [kernel] Build + allow attn_qat_infer FP4 attention on sm_121a (DGX Spark) (#1598) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 04:09:39 -07:00
Haochen JiangSolitaryThinkerClaude Opus 5.5
 		e722023bd6 [perf] Wan kernel fusion: Triton-fused residual+LayerNorm+modulate inference path (#1708) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 04:08:07 -07:00
Shao DuanSolitaryThinkerClaude Opus 5.5
 		bc0191d775 [perf] Harden Ulysses agreement and tune bounded H3 transfers (#1807) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 04:01:53 -07:00
MagicBearmagicbearSolitaryThinkerClaude Opus 5.5
 		2d6e7d9b6b [feat]: MiniMax-H3 encoder split: dedicated text-encoder node group for 720p on DGX Spark (#1877) 
Co-authored-by: magicbear <magicbear@users.noreply.github.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 03:46:33 -07:00
Mac LeeSolitaryThinkerClaude Opus 5.5
 		f60514183c [ci] Separate performance behavior tests (#1620) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 03:43:12 -07:00
William LinandClaude Opus 5.5 6d6195a9f1 [feat]: fp8 PV mode for the FA4-FP4 attention path (#1654) 
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 03:36:54 -07:00
Aryan KumarAryan Kumarcoderabbitai[bot]CodeRabbitSolitaryThinkerClaude Opus 5.5
 		2452022f15 [new-model] Add LTX-2.5 inference support (#1704) 
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: CodeRabbit <noreply@coderabbit.ai>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 03:34:18 -07:00
IshanClaude Sonnet 5SolitaryThinker
 		4b3f99b224 [new-model] Added LingBot-World-Fast image-to-video support (#1665) 
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-10-07 03:32:38 -07:00
YanghaoWilliam LinSolitaryThinkerClaude Opus 5.5
 		d5287f8352 [feat]: add MiniMax H3 Ref2VA and LoRA training support (#1757) 
Co-authored-by: William Lin <8941107+SolitaryThinker@users.noreply.github.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 03:21:45 -07:00
Joy JeffersonSolitaryThinkerClaude Opus 5.5
 		c18436125a [misc]: Refactor separate training pipeline runner (#1696) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 03:19:21 -07:00
page: FlappyBobSolitaryThinkerClaude Opus 5.5
 		37b9dc1836 [new-model] Add native Helios-Distilled T2V pipeline (#1670) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 03:18:24 -07:00
Shao DuanWilliam LinSolitaryThinkerClaude Opus 5.5
 		6102fac00d [bugfix]: fix modular ops activation checkpoint recomputation (#1716) 
Co-authored-by: William Lin <8941107+SolitaryThinker@users.noreply.github.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 02:41:12 -07:00
alanhuangyooSolitaryThinkerClaude Opus 5.5
 		1ad33c1832 [feat] Support training_cfg_rate > 0 for LTX-2 (#1752) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 02:38:42 -07:00
Mac LeeSolitaryThinkerClaude Opus 5.5
 		da87973412 [ci] Clarify dashboard cohort grouping for legacy v1 records (#1613) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 02:33:18 -07:00
William LinandClaude Opus 5.5 a3fd1d0bab [ci]: prevent direct tests from minting suite gates (#1615) 
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 02:32:48 -07:00
Kyle HuWilliam LinSolitaryThinkerClaude Opus 5.5
 		fb5efebdab [feat] Add HunyuanVideo 1.5 T2V training support (#1662) 
Co-authored-by: William Lin <willlin@nvidia.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 02:19:22 -07:00
YZJFSolitaryThinkerClaude Opus 5.5
 		6e4813f8b4 [bugfix] use in-process executor for num_gpus=1 (#1755) (#1879) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 02:18:23 -07:00
Yogya MehrotraClaude Fable 5SolitaryThinker
 		13ef81e6da [ci] Surface worker process logs on perf hard regressions (#1701) 
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-10-07 02:14:02 -07:00
Suhaan KhuranaSuhaanCommitsClaude Fable 5SolitaryThinker
 		ef62ac48d1 [new-model] Add Wan2.2-S2V-14B speech-to-video (model port + checkpoint converter) (#1683) 
Co-authored-by: SuhaanCommits <suhaan@cedar.build>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-10-07 01:36:01 -07:00
Raghav KSolitaryThinkerClaude Opus 5.5
 		00cb7d0ba2 [ci] Add DGX Spark (GB10) single-GPU perf config + gpu_types gating (#1679) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 01:30:42 -07:00
jayzouSolitaryThinkerClaude Opus 5.5
 		69a6215e7f [feat] Add Dreamverse multimodal inputs and H3 routing (#1835) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 01:30:26 -07:00
Jack ChenSolitaryThinkerClaude Opus 5.5
 		abe98e87f5 [feat] Add phase-aware modular training performance metrics (#1826) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 01:30:11 -07:00
Kyle HuSolitaryThinkerClaude Opus 5.5
 		274b922d39 [misc]: surface GenerationResult.peak_memory_mb in the MiniMax H3 examples (#1785) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 01:29:56 -07:00
Kyle HuWilliam LinSolitaryThinkerClaude Opus 5.5
 		38966056d0 [ci]: make merge-gate startup reliable (#1762) 
Co-authored-by: William Lin <8941107+SolitaryThinker@users.noreply.github.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
 2026-10-07 01:29:42 -07:00
William Lin 33d81730e9 [feat]: Kandinsky 6 Lite: register the 3.2B checkpoints and add docs + cookbook recipes (#1927) 2026-10-06 17:09:53 -07:00
Aryan KumarAryan KumarAryan KumarSolitaryThinkerClaude Opus 5.5
 		02a027c49f [feat]: FastH3 on DGX Spark and Apple Silicon (#1920) 
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: Aryan Kumar <aryank@Aryans-Mac-Studio.local>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-06 12:17:11 -07:00
Aryan KumarAryan KumarAryan KumarSolitaryThinkerClaude Opus 5.5
 		8b51380466 [feat]: FastH3 on single RTX GPUs (#1919) 
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: Aryan Kumar <aryank@Aryans-Mac-Studio.local>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-06 11:37:01 -07:00
William LinleffffKirillshaoxiongduanClaude Opus 5.5
 		f06d824054 [feat]: add Kandinsky-6.0 TI2VA and VSR pipelines (#1924) 
Co-authored-by: leffff <levnovitskiy@gmail.com>
Co-authored-by: Kirill <kykozlov@gmail.com>
Co-authored-by: shaoxiongduan <shaoxiongduan@gmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-06 10:50:17 -07:00
YZJFSolitaryThinkerClaude Sonnet 5.5
 		a4d6416c52 [docs] Add OpenAI serving recipes for Wan cookbook pages (#1906) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Claude Sonnet 5.5 <noreply@anthropic.com>
 2026-10-04 12:20:06 -07:00
William LinDavids048Claude Opus 5.5
 		8444c0897a [feat] FastH3 Ref2VA PDD inference with reference-video VSA sparsity (#1907) 
Co-authored-by: Davids048 <jundasu@ucsd.edu>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
 2026-10-02 11:28:07 -07:00
Junda Su 9edc8adf5f [misc] Move test-suite environment access into the registry and allowlists (#1898) 2026-09-30 00:15:39 -07:00
Junda Su 02f1ce11ae [misc] Move environment var reads into env registry and rename unprefixed variables (#1897) 2026-09-29 14:36:16 -07:00
Aryan KumarandAryan Kumar 7f03e03dc6 [docs]: FastH3 V2 cookbook serving and MLX install guide (#1884) 
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
 2026-09-29 13:03:18 -07:00
Junda Su e3b88bb12a [feat] Add a typed environment-variable registry, policy doc, and contract test (#1896) 2026-09-29 12:50:45 -07:00
Kyle Hu 81f3fec7fd [bugfix]: workers killed by a signal now log the reason (#1725) 2026-09-24 17:06:55 -07:00
Aryan Kumar 361f919c88 [feat]: add a narrow FastH3 8-step MLX ladder 
Keep the four-step uniform AdaLN cache, and use explicit DMD rungs only when the snapshot declares its own scheduler shifts.
 2026-09-23 11:06:55 -07:00
KeithandSolitaryThinker c4824c7764 [bugfix] FP8: gate the ROCm _scaled_mm path on CDNA4 (gfx950) instead of the capability tuple (#1859) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-09-16 19:58:55 -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
sudhirpol522 8839ba8d4d [bugfix] Add OpenAI-compatible image generation endpoint (#1840) 2026-09-14 17:55:56 -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
William Lin 556ac7088e [refactor] Simplify Wan sampling and tests (#1825) 2026-09-07 15:57:19 -07:00
William Lin 7f83164233 [refactor] Move Wan VAE into the Wan package (#1824) 2026-09-05 18:43:55 -07:00
William Lin e19913f6e9 [refactor] Group Wan transformer and config (#1823) 2026-09-05 17:05:32 -07:00