Commit Graph
36 Commits
Author SHA1 Message Date
fba967ed9c [diffusion] Support diffusion decoder parallel tiling for LTX-2.5 (#36026)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Mick Qian <mickqian@users.noreply.github.com>
2026-09-08 10:01:06 +08:00
Yihao Wang 667bc043dc [CI] remove MINIMAX_H3_HF_TOKEN (#37687) 2026-09-04 09:22:32 +08:00
Yihao WangandClaude Fable 5 f5bed255c0 [diffusion] feat: support key masks on USPAttention's replicated-prefix path (#36735)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-09-03 20:13:33 +08:00
Yihao WangandClaude Fable 5 14444c6a04 [diffusion] feat: add maybe_record_function profiler spans for request phases (#35922)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-09-03 20:12:54 +08:00
Yihao WangandClaude Fable 5 7088f21922 [diffusion] fix: make tail_attn_meta cuda-graph capturable (#36658)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-08-28 12:22:07 +08:00
Yihao WangandClaude Opus 5 d7baad0116 [diffusion] Keep the Cosmos3 Super DiT resident on high-memory GPUs (#36375)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
2026-08-25 21:10:39 -07:00
Yihao Wang ba8e601358 [docs] fix note formatting in sglang-d documentation (#35761) 2026-08-20 16:39:39 -07:00
5c0ace30c0 [diffusion] model: support ltx-2.5 (#34471)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-08-15 23:36:02 +08:00
Yihao WangandClaude Opus 5 acb64db9e2 [diffusion] fix: enable bcg with tp (#33421)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-07 19:01:05 +08:00
Yihao Wang 227dadd79a [diffusion] feat: support resident layers for DiT (#31538) 2026-07-29 16:52:55 +08:00
Yihao Wang 9ea964a535 [diffusion] fix: per-shard FP8 scale shape for single-GPU fused linears (#32157) 2026-07-28 20:28:01 -07:00
Yihao Wang 95865de24f [diffusion] CI: read consistency GT from ci-data-diffusion at per-platform commit (#32297) 2026-07-25 09:55:57 +08:00
Yihao Wang ebf5330f71 [diffusion] CI: enhance diffusion GT publishing with per-platform directory resolution (#32282) 2026-07-25 09:54:46 +08:00
Yihao Wang 433429b16a diffusion: skip _save_gt_output for 3d/mesh (#32117) 2026-07-24 08:14:05 +08:00
Yihao Wang 7de33ce806 fix: fix mm processor double bos (#26505) 2026-07-11 07:53:08 +08:00
Yihao WangandClaude Opus 4.8 68901ba387 [diffusion] Support SP for Krea-2 (#29777)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-07 19:39:00 -07:00
Yihao WangandClaude Opus 4.8 a531d81c19 [diffusion][cache-dit] support Krea-2 + run-driven has_separate_cfg (#29688)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-30 08:22:05 -07:00
Yihao Wang dd4caf9459 [Docs] fix SGLang-diffusion installation links (#29139) 2026-06-24 09:46:06 -07:00
Yihao WangandClaude Opus 4.8 5beddc8afc [Diffusion] Add Krea 2 support (#29052)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-23 22:56:51 -07:00
Yihao Wang 83d32fbc2f remove lora section (#29056) 2026-06-23 16:26:51 +00:00
Yihao Wang b5e0965b07 [Diffusion][Cookbook] Add Krea-2 cookbook (#29051) 2026-06-23 08:02:08 -07:00
Yihao Wang f5c9f88ee2 [plugin][distributed] use active platform's backend in get_default_distributed_backend (#23969) 2026-06-11 20:05:17 -07:00
Yihao Wang b4bed8c398 [diffusion] fix: cast to float32 (from float64) in triton kernel to unblock torch.compile (#27709) 2026-06-11 10:29:21 +08:00
bdf47315ce docs: add cookbook for SANA-WM (#27198)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-06-09 10:47:32 +08:00
32bedbf88e [diffusion] model: support SANA-WM with streaming support (#27531)
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: sjmshsh <88866917+sjmshsh@users.noreply.github.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-06-09 01:10:14 +08:00
Yihao Wang 8980eb82de [Docs] Update Nemotron3-Nano-Omni cookbook to reflect new model paths (#25198) 2026-06-03 14:55:30 -07:00
Yihao Wang 41eb2d861b [fix] load_audio: fall back to soundfile when torchcodec fails on WAV with trailing metadata (#24185) 2026-05-14 15:02:49 +08:00
Yihao Wang b35fd5f104 [fix] skip legacy minicpmv conv template for MiniCPM-V 4.6 (#24998) 2026-05-12 15:27:28 +08:00
Yihao Wang 0f3932c055 [Fix] Qwen3-ASR config: set thinker_config before super().__init__ (#24187) 2026-05-12 11:52:15 +08:00
Yihao Wang 7407a62c1c [Docs] Update MiniCPM-V-4.6 documentation and deployment configuration (#24991) 2026-05-11 11:10:19 -07:00
Yihao Wang 9f066cb55b [Docs] Add MiniCPM-V 4.6 cookbook (#24876) 2026-05-10 21:32:15 -07:00
Yihao Wang 9150e77399 [Model] Add MiniCPM-V 4.6 support (#24855) 2026-05-10 12:24:17 -04:00
Yihao Wang 0acc569edd [Bench] extend MMMU answer extractor with explicit-commit patterns (#24084) 2026-04-30 19:08:08 -07:00
Yihao Wang 903e46d848 [Bench] fix bench_hf.py KeyError + reduce print spam + add --limit (#24079) 2026-04-29 11:43:37 -07:00
Yihao Wang a5ed507a16 [refactor] [asr] add transcription adapter for extensible ASR models support (#22181) 2026-04-09 01:19:37 +08:00
Yihao Wang ae8da14ea3 [fix] [whisper] ensure inputs are moved to the correct device before processing. (#22293) 2026-04-08 23:45:42 +08:00