Didan Deng 43ec7f701b [Feature] Flash Attention to Support Attention Mask (#760) ...

Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com>

2026-01-16 11:01:11 +08:00

..

bagel

[Bagel]Add image edit (#588)

2026-01-05 12:18:04 +08:00

longcat_image

[Diffusion][Feature] Implement SP support in LongCatImageTransformer (#721)

2026-01-12 00:22:50 -08:00

ovis_image

[core] add torch compile for diffusion (#684)

2026-01-09 04:05:44 +13:00

qwen_image

[Feature] Flash Attention to Support Attention Mask (#760)

2026-01-16 11:01:11 +08:00

sd3

[Bugfix] Fix stable diffusion3 compatibility error (#772)

2026-01-13 21:12:32 +08:00

stable_audio

[Model] Add Stable Audio Open support for text-to-audio generation (#331)

2026-01-07 17:01:06 +08:00

wan2_2

[bugfix] Fix Wan2.2 I2V warmup failure by adding support_image_input attribute (#791)

2026-01-15 13:14:34 +00:00

z_image

[Feat] Enable DiT tensor parallel for Diffusion Pipeline(Z-Image) (#735)

2026-01-12 11:00:42 +08:00

__init__.py

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

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

interface.py

[core] add torch compile for diffusion (#684)

2026-01-09 04:05:44 +13:00