Ding Zuhaoand汪志鹏 283a62fd76 [Feature] [HunyuanImage3] Add TeaCache support for inference acceleration (#1927) ...

Signed-off-by: Ding Zuhao <e1583181@u.nus.edu>
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
Co-authored-by: 汪志鹏 <wangzhipeng628@gmail.com>

2026-03-28 15:24:21 +00:00

..

__init__.py

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

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

autoencoder.py

[Model] SupportHunyuanImage3 Diffusion Model in vllm-omni (#1085)

2026-02-10 03:03:44 +13:00

hunyuan_fused_moe.py

[Bugfix][HunyuanImage3.0] Fix default guidance_scale from 1.0 to 4.0 and port GPU MoE ForwardContext fix from NPU (#2142)

2026-03-28 13:49:03 +08:00

hunyuan_image_3_tokenizer.py

[Model] SupportHunyuanImage3 Diffusion Model in vllm-omni (#1085)

2026-02-10 03:03:44 +13:00

hunyuan_image_3_transformer.py

[Feature] [HunyuanImage3] Add TeaCache support for inference acceleration (#1927)

2026-03-28 15:24:21 +00:00

pipeline_hunyuan_image_3.py

[Feature] support sp for hunyuan (#2163)

2026-03-27 17:28:13 +08:00