nodes/hao-ai-lab-FastVideo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
950 Commits 339 Branches 8 Tags
129fcaffaba94792cfade39d72a04b127c295429
Commit Graph
43 Commits
Author SHA1 Message Date
Will LinandClaude Fable 5 129fcaffab [perf] inference: regional fullgraph torch.compile of the DiT blocks (port of #1718 to the inference path) 
Extend the training-side regional-compile port (internal 863e87342, GO
verdict vsa_gate/compile_ab/VERDICT.md) to inference so every H3 run can
compile the 52 transformer blocks. Opt-in and off by default:

- New FastVideoArgs.inference_torch_compile (CLI --inference-torch-compile),
  env FASTVIDEO_INFERENCE_TORCH_COMPILE=1 folded in __post_init__ (the
  attention_backend parse-once pattern), reachable through
  PipelineSelection.experimental {"inference_torch_compile": true} exactly
  like the VSA_sparsity / VSA_tile_size knobs.
- maybe_load_fsdp_model applies the compile right after the transformer
  loads: per-_compile_conditions block, fullgraph=True + inductor
  options.emulate_precision_casts injected, no user kwargs needed (the
  compile-A/B verdict recipe). prepare_for_compile still runs first, so the
  H3 fusion-inertness warning of #1735 is preserved.
- _regional_compile_unsupported_reason ported from the training loader:
  VSA / VSA-H3 backends and the FASTVIDEO_DISABLE_ATTENTION_COMPILE=1
  escape hatch degrade the transformer to eager with one warning; FLASH_ATTN
  on flash-attn 3 is rejected with an actionable message. FA4/FA2/SDPA
  compile through their existing custom-op boundaries (forward-only is
  enough at inference; the training port's backward custom ops are not
  needed under no_grad).
- FASTVIDEO_DISABLE_ATTENTION_COMPILE default flipped to 0 (attention is
  traced by default), matching the training port and upstream #1718 —
  eager runs are unaffected (torch.compiler.disable is inert outside
  dynamo).
- enable_torch_compile + inference_torch_compile together skip the
  pipeline-level DiT compile (the loader already owns those forwards).
- examples: --inference-torch-compile on basic_minimax_h3_t2v.py (dense
  target) and basic_fasth3.py (exercises the VSA degrade path).
- CPU-safe contract tests for the guard and the kwargs injection.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
 2026-08-22 02:56:30 +00:00
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
Kai 0653f8f3af [new-model] Add V2A: native MMAudio inference pipeline (#1622) 2026-08-09 17:29:27 -07:00
William Lin 9028953625 [misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702) 2026-08-08 22:24:17 -07:00
Kaiqin Kong e8b0e4c61e [feat] Add MiniMax H3 (#1674) 2026-08-04 13:54:39 -07:00
William Lin 7b094c945b [refactor]: resolve attention backend once per component at load time (#1657) 2026-08-02 15:07:42 -07:00
Junda Su d4bdd3621a [new-model] Port LingBot-World-v2 (#1579) 2026-07-16 19:51:53 -07:00
Raghav KMrinaal DograSolitaryThinker
 		6966f9e0bc [fix] Z-Image (#1236) draft port: rebase + strict-load contract + bf16 encoder parity + PORT_STATUS (#1339) 
Co-authored-by: Mrinaal Dogra <mdogra@ucsd.edu>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-07-16 18:18:25 -07:00
Shreejith SGandH1yori233 d82abc271e [feat] Add GLM-Image inference support (#1030) 
Co-authored-by: H1yori233 <k1kong@ucsd.edu>
 2026-07-12 22:42:42 -07:00
Aryan KumarAryan KumarleffffSolitaryThinker
 		02e1143f22 [feat] Add Kandinsky-5 T2V/I2V pipeline support (#1471) 
Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>
Co-authored-by: leffff <levnovitskiy@gmail.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-07-07 14:43:30 -07:00
alexzmsWilliam LinLoay RashidKaiqin Kongmergify[bot]
 		e60601df7f [feat] QAD 5090: QAT training recipe — finetune + DMD distillation (12/12) (#1462) 
Co-authored-by: William Lin <SolitaryThinker@users.noreply.github.com>
Co-authored-by: Loay Rashid <42599591+loaydatrain@users.noreply.github.com>
Co-authored-by: Kaiqin Kong <k1kong@ucsd.edu>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-06-17 15:18:52 -07:00
William LinGnav3852Mac Lee
 		d922ab2cbc [model] Flux2 Klein Port (#1349) 
Co-authored-by: Gnav3852 <63612880+Gnav3852@users.noreply.github.com>
Co-authored-by: Mac Lee <macthecadillac@gmail.com>
 2026-06-09 14:55:55 -07:00
Kaiqin KongandSolitaryThinker afdb6fbfa5 [feat] Add MatrixGame3.0 (#1201) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2026-05-27 21:07:01 +00:00
Junda SuSolitaryThinkerMatthew NotoXOR-opZhang Peiyuan
 		b4de5a9f1b [feat] Dreamverse 12/14: Add LTX2 refine and upsampler support (#1335) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: Matthew Noto <99706358+RandNMR73@users.noreply.github.com>
Co-authored-by: XOR-op <17672363+XOR-op@users.noreply.github.com>
Co-authored-by: Zhang Peiyuan <42993249+jzhang38@users.noreply.github.com>
 2026-05-15 12:21:40 -07:00
William Lin 424c643b6e [feat]: MagiHuman pipeline stages (4/8) (#1298) 2026-05-12 14:59:21 -07:00
William Lin c77a76c6af [feat] Stable Audio Open 1.0: T2A + A2A + RePaint inpainting (native) (#1260) 2026-05-01 00:07:11 -07:00
vishruthb 5789955bbe [feat] add gen3c (cosmos-7b) model and pipeline support (#1059) 2026-04-01 11:42:02 +00:00
Zhang Peiyuan 03d9ce2edb [Misc] Remove StepVideo (#1118) 2026-02-21 17:15:42 -08:00
Zhang PeiyuanRandNMR73JerryZhou54Davids048Peiyuan Zhang
 		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
IshanandJinzhe Pan 0aff68f51d [Feat] Add Stable Diffusion 3.5 (#1075) 
Co-authored-by: Jinzhe Pan <eigensystem1318@gmail.com>
 2026-02-10 14:31:36 +08:00
Wei Zhou 98308db7e0 [Feature] [Hy1.5] Support HY1.5 super-resolution pipeline for 1080p videos (#1046) 2026-02-05 16:39:20 -08:00
Mingjia Huo 59e00f6164 [feat] Add HY-World1.5-Bidirectional-480P-I2V (#1027) 
VAE requires further improvement, will raise PR in near future.
 2026-01-23 14:18:04 -08:00
Shao DuanandWill 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
XOR-op 785d123e36 [feat] Hooks API and layerwise offloading for all DiTs (#1006) 2026-01-17 11:22:02 -08:00
William Lin 0f53b51e6c [CI] Fix OOM issues in ssim tests (#1011) 2026-01-16 21:15:20 -08:00
KyleShao dbddfab6d2 [feat] Introduce Cosmos 2.5 Text2World pipeline (#974) 2026-01-15 15:09:05 -08:00
Ohm-Rishabh d83f45a6a0 Layer offloading (#966) 2026-01-03 21:46:00 -08:00
XOR-op dd91542cd1 [feat] Support text encoder weight override and quantization (#983) 2026-01-03 15:33:33 -06:00
alexzmsandShao 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
Wei Zhou 1f70032af5 [New Model] Hunyuan1.5 (#943) 2025-12-21 00:57:52 -06:00
Jinzhe PanandXingyu Long f4c58894d9 [Feat] add ray support (#838) 
Co-authored-by: Xingyu Long <xingyulong97@gmail.com>
 2025-10-16 23:17:54 -07:00
zyang6andkiritorl 87489f0872 Add wan2.1 functionality support for Ascend NPU platform (#810) 
Co-authored-by: kiritorl <1021709528@qq.com>
 2025-10-09 16:25:08 -07:00
William Lin 490bde90e1 [bugfix] Allow overriding dit checkpoint for inference and Lower VSA LR in example scripts (#831) 2025-10-05 01:44:49 -07:00
RandNMR73SolitaryThinkergemini-code-assist[bot]
 		dc7596b973 [self-forcing][8/n] Self-Forcing For Wan2.2-A14B + torch.compile training and distillation support (#818) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-10-02 15:01:45 -07:00
William Lin 404cbf4f3c [self-forcing] [6/n] Add Ode Init training (#811) 2025-09-22 17:58:19 -07:00
Wei ZhouRandNMR73SolitaryThinker
 		31f000d1cc [self-forcing] [5/n] Add Self-Forcing distillation pipeline (#808) 
Co-authored-by: RandNMR73 <notomatthew31@gmail.com>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2025-09-20 19:32:10 -07:00
Jinzhe Pan f2bc037fff [Fix] training pipeline pin_cpu_memory issue (#692) 2025-08-07 02:31:20 -07:00
Wei ZhouandSolitaryThinker c41305ad18 [Feat] Add Wan2.2 14B MoE (#688) 
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
 2025-08-06 20:31:03 -07:00
Wenxuan Tan 6c81befc87 [Feature] Optionally enable torch compile (#684) 2025-08-01 20:17:40 -07:00
Yongqi Chen 247fe273d8 [Feature] Add DMD T2V training pipeline (#651) 2025-07-27 03:35:51 -04:00
William Lin 81c9df629c [core] Add offloading for vae and image encoder and rename offloading args (#643) 2025-07-25 17:55:03 -07:00
William Lin f572319bd9 [Feature] Remove V1 folder (#642) 2025-07-24 22:43:12 -07:00