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

..

layers

[Perf][Hunyuan] Optimize for vae and patch_embed (#6306)

2026-08-20 16:29:21 +00:00

__init__.py

[Perf][Hunyuan] Optimize for vae and patch_embed (#6306)

2026-08-20 16:29:21 +00:00

autoencoder.py

[Perf][Hunyuan] Optimize for vae and patch_embed (#6306)

2026-08-20 16:29:21 +00:00

hunyuan_image3_tokenizer.py

[Rebase] Rebase to vllm 0.26.0 (#5443)

2026-07-27 23:35:49 +08:00

hunyuan_image3_transformer.py

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

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

pipeline_hunyuan_image3.py

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

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

prompt_utils.py

Fix hunyuan resolve stop token ids (#3896)

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

request_layout.py

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

2026-08-10 08:48:56 +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