vllm-omni

audiox

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

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

bagel

[Refactor] Rename SupportsModuleOffload to SupportsComponentDiscovery (#3354 )

2026-05-08 14:16:49 +00:00

cosyvoice3_audio

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

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

diffusers_adapter

[Diffusion][Attention] Support per-role attention backend via CLI (#2681 )

2026-05-10 11:59:05 +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

[Feat] support HSDP for DreamID-Omni (#3138 )

2026-05-06 13:09:39 +08:00

ernie_image

[Feat] ERNIE image model (T2I) (#2861 )

2026-05-03 15:53:28 +08:00

flux

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

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

flux2

（Phase 1）Add ModelOpt FP8 auto-detect support for diffusion checkpoints #2709 (#2913 )

2026-05-09 16:55:05 +08:00

flux2_klein

（Phase 1）Add ModelOpt FP8 auto-detect support for diffusion checkpoints #2709 (#2913 )

2026-05-09 16:55:05 +08:00

glm_image

[Feat] support quantization for GLM-IMAGE (#2292 )

2026-04-24 13:49:49 +08:00

helios

perf(helios): replace strided RoPE with stack+flatten for contiguous memory (#2474 )

2026-04-19 20:28:48 +08:00

hunyuan_image3

[Feature] hunyuanimage support flash attn (#2981 )

2026-05-10 22:08:24 +08:00

hunyuan_video

[Feat] Add Sequence Parallelism (USP) support for HunyuanVideo 1.5 transformer (#2444 )

2026-05-08 21:20:03 +08:00

internvla_a1

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

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

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

[Refactor] Rename SupportsModuleOffload to SupportsComponentDiscovery (#3354 )

2026-05-08 14:16:49 +00:00

magi_human

[Refactor] Replace and ban a few torch.cuda functions in favor of torch.accelerator replacements. (#3365 )

2026-05-07 23:23:59 +08:00

mammoth_moda2

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

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

nextstep_1_1

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

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

omnigen2

[Bugfix] fix OmniGen2 offload and dtype mismatch (#2560 )

2026-05-09 09:13:37 +08:00

omnivoice

[Bugfix][OmniVoice] Read voice-cloning fields from OmniTextPrompt in offline path (#3392 )

2026-05-07 06:17:57 +08:00

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

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

2026-05-08 21:37:57 +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

[Bugfix] Fix Dtype Crashes in SD3 (#2526 )

2026-05-08 16:05:38 +08:00

stable_audio

[Bugfix][StableAudio] Pass model_class_name to Omni() and declare audio class attrs (#3405 )

2026-05-09 06:40:43 +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

[Diffusion][Attention] Support per-role attention backend via CLI (#2681 )

2026-05-10 11:59:05 +08:00

z_image

（Phase 1）Add ModelOpt FP8 auto-detect support for diffusion checkpoints #2709 (#2913 )

2026-05-09 16:55:05 +08:00

__init__.py

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

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

interface.py

[Refactor] Rename SupportsModuleOffload to SupportsComponentDiscovery (#3354 )

2026-05-08 14:16:49 +00:00

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