baonudesifeizhai 076c34abfb （Phase 2）Add ModelOpt mixed FP8/NVFP4 support for image generation (#3570) ...

Signed-off-by: roG0d <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>

2026-05-22 10:39:10 +08:00

..

__init__.py

[Fix] HunyuanImage-3.0: unify naming hunyuan_image_3 → hunyuan_image3 (#2712)

2026-04-14 21:53:47 -07:00

autoencoder.py

[Fix] HunyuanImage-3.0: unify naming hunyuan_image_3 → hunyuan_image3 (#2712)

2026-04-14 21:53:47 -07:00

hunyuan_fused_moe.py

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

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

hunyuan_image3_tokenizer.py

[Feature][Hunyuan image 3.0] AR + DIT with kv reuse. (#3346)

2026-05-08 20:51:46 +08:00

hunyuan_image3_transformer.py

（Phase 2）Add ModelOpt mixed FP8/NVFP4 support for image generation (#3570)

2026-05-22 10:39:10 +08:00

pipeline_hunyuan_image3.py

[Feat] Enable VAE parallel in HunyuanImage3 (#3091)

2026-05-20 09:55:33 +08:00

prompt_utils.py

[Feature] HunyuanImage-3.0 IT2I: multi-image input + prompt API cleanup (#3444)

2026-05-14 16:58:40 +08:00

system_prompt.py

[Fix] HunyuanImage-3.0: unify naming hunyuan_image_3 → hunyuan_image3 (#2712)

2026-04-14 21:53:47 -07:00