Alex Brooksand汪志鹏 7ff11d8d0f [Perf/Fix] Reimplement Batched CFG Forward for Bagel (#4098) ...

Signed-off-by: Alex Brooks <albrooks@redhat.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>

2026-06-22 07:37:21 +08:00

..

audiox

[Diffusion] [Model] Support AudioX (#2077)

2026-05-04 10:24:35 -04:00

bagel

[Perf/Fix] Reimplement Batched CFG Forward for Bagel (#4098)

2026-06-22 07:37:21 +08:00

cosmos3

Improve Cosmos3 v2v quality (#4514)

2026-06-21 22:20:30 +08:00

cosyvoice3_audio

[Cleanup] Extract shared SinusPositionEmbedding/DiTTimestepEmbedding/timestep_embedding layer (#3285)

2026-05-01 20:19:42 +08:00

diffusers_adapter

[BugFix] Rename attention_config to diffusion_attention_config (#3489)

2026-05-11 11:27:35 +08:00

dmd2

enhancement: extend to dmd2 to image generation + add flux, qwen image pipelines (#2974)

2026-05-08 21:37:57 +08:00

dreamid_omni

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

dreamzero

[Perf][DreamZero]dreamzero supports CUDA graph, torch.compile, and DiT Caching. (#4213)

2026-06-19 14:24:37 +08:00

ernie_image

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

flux

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

flux2

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

flux2_klein

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

glm_image

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

gr00t

[Diffusion] add GR00T-N1.7 pipeline with OpenPI serving (#3798)

2026-06-20 11:45:26 +08:00

helios

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

hidream_image

[Cleanup] Remove duplicate HiDreamI1ImagePipeline (fixes #4009) (#4045)

2026-06-19 06:32:18 +08:00

hunyuan_image3

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

hunyuan_video

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

internvla_a1

[Model] Add InternVLA-A1 offline inference support (#2737)

2026-04-27 02:28:07 -07:00

lance

[BugFix]: Fix Bagel generate_image denoising schedule (#4509)

2026-06-18 02:02:38 +00:00

longcat_image

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

ltx2

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

magi_human

[Refactor] Migrate existing pipelines to use SupportsComponentDiscovery for offload discovery (#3076)

2026-06-17 21:33:06 +08:00

mammoth_moda2

[Refactor] Migrate existing pipelines to use SupportsComponentDiscovery for offload discovery (#3076)

2026-06-17 21:33:06 +08:00

ming_flash_omni

[Model] Add Ming-flash-omni-2.0 Image Generation (Diffusion) Stage (#2875)

2026-05-27 23:21:20 +08:00

mistral_encoder

[Model] Add TP-aware MistralEncoder for FLUX.2-dev TP (#2465)

2026-05-13 12:33:55 -07:00

nextstep_1_1

[Refactor] Migrate existing pipelines to use SupportsComponentDiscovery for offload discovery (#3076)

2026-06-17 21:33:06 +08:00

omnigen2

[Bugfix] harden diffusion model prefetch against transformers v5 shard-resolution race (#4076)

2026-06-04 12:14:25 +08:00

omnivoice

[Feat]Support Nonverbal Tags in OmniVoice (#3968)

2026-06-01 15:51:05 +08:00

ovis_image

[Refactor] Migrate existing pipelines to use SupportsComponentDiscovery for offload discovery (#3076)

2026-06-17 21:33:06 +08:00

qwen_image

[Refactor] Migrate existing pipelines to use SupportsComponentDiscovery for offload discovery (#3076)

2026-06-17 21:33:06 +08:00

schedulers

enhancement: extend to dmd2 to image generation + add flux, qwen image pipelines (#2974)

2026-05-08 21:37:57 +08:00

sd3

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

sdxl

[SDXL] SDXL model enabling (#4331)

2026-06-16 22:51:11 +08:00

sensenova_u1

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

stable_audio

[Cache Refactor 1/N] Simplify CacheDiT Integration (#2527)

2026-06-20 08:30:44 +08:00

t5_encoder

[Bugfix] T5 text encoder to render correct text in FLUX.1-dev (#2760)

2026-04-24 18:01:52 +08:00

wan2_2

[Refactor] Migrate existing pipelines to use SupportsComponentDiscovery for offload discovery (#3076)

2026-06-17 21:33:06 +08:00

z_image

[Refactor] Migrate existing pipelines to use SupportsComponentDiscovery for offload discovery (#3076)

2026-06-17 21:33:06 +08:00

__init__.py

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

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

interface.py

[Feature] Add HunyuanImage3 DiT grouped step batching (#4041)

2026-06-15 20:36:41 +08:00

progress_bar.py

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

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

utils.py

[Quantization] Redo Z-Image text encoder FP8 online quantization (#3279)

2026-05-06 16:37:36 +00:00