Zhengyuan Su (苏政渊)andClaude Opus 4.6 92c788e5fd [Misc] Clean up method name in BAGEL. (#2501) ...

Signed-off-by: Zhengyuan Su <su.zhengyuan@u.nus.edu>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-09 14:55:15 +08:00

..

bagel

[Misc] Clean up method name in BAGEL. (#2501)

2026-04-09 14:55:15 +08:00

cosyvoice3_audio

[Model] Fun cosy voice3-0.5-b-2512 (#498)

2026-03-04 19:54:59 -05:00

dreamid_omni

[bugfix]bugfix dreamid (#2125)

2026-04-07 12:06:58 +08:00

flux

Add supports_float64() to OmniPlatform and clean up MPS (#2488)

2026-04-07 11:15:02 +08:00

flux2

Add supports_float64() to OmniPlatform and clean up MPS (#2488)

2026-04-07 11:15:02 +08:00

flux2_klein

[Feat] support for multi-block layerwise offloading, fix top-level parameters/buffers staying on CPU (#1486)

2026-04-06 11:49:35 +08:00

glm_image

[Feat] support HSDP for Qwen-image series, Z-Image, GLM-Image (#2029)

2026-04-01 20:01:09 +08:00

helios

[Feat] support for multi-block layerwise offloading, fix top-level parameters/buffers staying on CPU (#1486)

2026-04-06 11:49:35 +08:00

hunyuan_image_3

[HunyuanImage3] Align system_prompt support with official implementation (#2270)

2026-04-07 15:37:17 +08:00

hunyuan_video

[Feat] support for multi-block layerwise offloading, fix top-level parameters/buffers staying on CPU (#1486)

2026-04-06 11:49:35 +08:00

longcat_image

[Feat] Enable Layerwise CPU offloading for SD3.5, Ovis-Image, Nextstep_1, LongCat-Image (#2339)

2026-04-08 09:55:09 +08:00

ltx2

[Diffusion] Refactor LTX2 to use unified CFG parallel framework (#2160)

2026-04-08 11:44:04 +08:00

magi_human

[MagiHuman] Fix audio sample rate and fps propagation for online serving (#2554)

2026-04-09 06:52:12 +00:00

mammoth_moda2

Add supports_float64() to OmniPlatform and clean up MPS (#2488)

2026-04-07 11:15:02 +08:00

nextstep_1_1

[Feat] Enable Layerwise CPU offloading for SD3.5, Ovis-Image, Nextstep_1, LongCat-Image (#2339)

2026-04-08 09:55:09 +08:00

omnigen2

Add supports_float64() to OmniPlatform and clean up MPS (#2488)

2026-04-07 11:15:02 +08:00

omnivoice

[OmniVoice] Add two-stage TTS serving support (#2463)

2026-04-03 20:41:20 +00:00

ovis_image

[Feat] Enable Layerwise CPU offloading for SD3.5, Ovis-Image, Nextstep_1, LongCat-Image (#2339)

2026-04-08 09:55:09 +08:00

qwen_image

[Feat] support for multi-block layerwise offloading, fix top-level parameters/buffers staying on CPU (#1486)

2026-04-06 11:49:35 +08:00

schedulers

[bugfix] use unipc scheduler for Wan 2.2 (#804)

2026-01-16 12:31:25 +00:00

sd3

[Feat] Enable Layerwise CPU offloading for SD3.5, Ovis-Image, Nextstep_1, LongCat-Image (#2339)

2026-04-08 09:55:09 +08:00

stable_audio

[Performance] diffusion timing (#1757)

2026-03-19 12:26:12 +08:00

t5_encoder

[Model Support]: Magihuman support (#2301)

2026-04-04 09:29:09 +00:00

wan2_2

[Perf] Wan2.2 I2V optimization: convert datatype from FP32 to BF16 in vae (#2391)

2026-04-08 03:26:39 +00:00

z_image

[Feat] image2image for Z-Image (#1580)

2026-04-08 14:41:24 +08:00

__init__.py

[Bugfix] Remove mandatory flash-attn dependency and optimzie docs (#113)

2025-11-30 18:20:44 +08:00

interface.py

reafator pipeline stage/step pipeline (#1368)

2026-03-20 19:21:50 +08:00

progress_bar.py

[UX] Add progress bar for diffusion models (#1652)

2026-03-05 23:56:14 +08:00