Wang fuyinandHongsheng Liu 72ee535fcd [Diffusion] Add native paged KV backend for diffusion workers (#6102) ...

Signed-off-by: Acerak01-fy <wfy2003324@163.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-08-22 21:45:45 +08:00

..

test_diffusion_kv_request.py

[Diffusion] Prepare HunyuanImage3 for Scheduler-managed paged KV cache (#5541)

2026-08-10 08:48:56 +08:00

test_hunyuan_image3_it2i_ar_format.py

[Feature] HunyuanImage-3.0 IT2I (image editing) support (#3107)

2026-05-06 22:37:39 +08:00

test_hunyuan_image3_it2i_multi_image.py

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

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

test_hunyuan_image3_rgb.py

[Bugfix][HunyuanImage3] Align AR RGB conversion with official semantics (#4502)

2026-06-22 16:09:03 +00:00

test_hunyuan_image3_sampler.py

[perf] avoid HunyuanImage3 timestep scalar sync (#4363)

2026-06-24 11:05:35 +08:00

test_hunyuan_image3_step_execution.py

[Diffusion] Prepare HunyuanImage3 for Scheduler-managed paged KV cache (#5541)

2026-08-10 08:48:56 +08:00

test_image_kv_cache_manager.py

[Diffusion] Add native paged KV backend for diffusion workers (#6102)

2026-08-22 21:45:45 +08:00

test_multi_resolution.py

[image][bugfix] Fix HunyuanImage3 bridge request batching (#4849)

2026-07-03 02:58:13 +00:00

test_prompt_utils.py

Fix hunyuan resolve stop token ids (#3896)

2026-05-31 07:47:36 +08:00