Joshna-Medisettyandgcanlin ca6c7ad2be Fix OmniGen2 transformer config loading for HF models (#1934) ...

Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
Signed-off-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>

2026-03-19 10:21:54 +08:00

..

bagel

[Bagel]: Support multistage img2img (#1669)

2026-03-09 22:23:50 +08:00

cosyvoice3_audio

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

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

dreamid_omni

[Diffusion] [Model] Dreamid omni (#1855)

2026-03-13 21:53:06 +08:00

flux

[Feat] support HSDP for Flux family (#1900)

2026-03-15 22:48:12 +08:00

flux2

[Feat] support HSDP for Flux family (#1900)

2026-03-15 22:48:12 +08:00

flux2_klein

[Feat] support HSDP for Flux family (#1900)

2026-03-15 22:48:12 +08:00

glm_image

[chore] add _repeated_blocks for regional compilation support (#1642)

2026-03-04 14:26:06 +08:00

helios

[Bugfix] Fix Helios text_encoder embed_tokens all-zeros due to untied weights (#1728)

2026-03-12 15:28:21 +00:00

hunyuan_image_3

[Model] Extend NPU support for HunyuanImage3 Diffusion Model (#1689)

2026-03-12 20:49:17 +08:00

longcat_image

[Refactor] Use SP Plan for LongCat Sequence Parallelism (#1772)

2026-03-13 11:13:34 +08:00

ltx2

[Model] support LTX-2 text-to-video image-to-video (#841)

2026-03-05 23:31:48 +08:00

mammoth_moda2

add support for MammothModa2 model (#336)

2026-03-04 22:52:56 +08:00

nextstep_1_1

[Model]Add new nextstep_1(Diffusion) model(only T2I) (#612)

2026-02-26 00:09:11 +08:00

omnigen2

Fix OmniGen2 transformer config loading for HF models (#1934)

2026-03-19 10:21:54 +08:00

ovis_image

[Refactor] lora: reuse load_weights packed mapping (#991)

2026-03-04 02:58:43 +00:00

qwen_image

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

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

schedulers

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

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

sd3

[Bugfix] Fix SD3.5-medium attn2 uninitialized weights (#1659)

2026-03-13 14:58:17 +08:00

stable_audio

Revert "Add online serving to Stable Audio Diffusion and introduce v1/audio/generate endpoint" (#1789)

2026-03-10 22:40:48 +08:00

wan2_2

[Perf] Reduce IPC overhead for single-stage diffusion serving for Wan2.2 (#1715)

2026-03-10 00:03:51 +13:00

z_image

[Feat] support SP for FLUX.2-klein (#1250)

2026-03-15 12:18:12 +08:00

__init__.py

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

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

interface.py

[Diffusion] [Model] Dreamid omni (#1855)

2026-03-13 21:53:06 +08:00

progress_bar.py

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

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