jiangmengyu18andbetta18 c174c95ab0 [NPU] [Quant] Support HunyuanImage3 offline quantization with vLLM-Ascend on diffusion path (#2979) ...

Signed-off-by: betta18 <jiangmengyu1@huawei.com>
Signed-off-by: jiangmengyu18 <56633611+jiangmengyu18@users.noreply.github.com>
Co-authored-by: betta18 <jiangmengyu1@huawei.com>

2026-04-25 06:14:01 +00:00

..

cache_acceleration

Codex revert pr reviewer (#2959)

2026-04-21 21:43:15 +08:00

parallelism

[skip ci][Doc] Refine the Diffusion Features User Guide (#1928)

2026-03-30 14:28:04 +08:00

quantization

[NPU] [Quant] Support HunyuanImage3 offline quantization with vLLM-Ascend on diffusion path (#2979)

2026-04-25 06:14:01 +00:00

attention_backends.md

[Doc] Add diffusion attention backend docs (#3011)

2026-04-23 11:30:47 +08:00

cpu_offload_diffusion.md

[Refactor] Let diffusion pipelines declare offloadable modules via SupportsModuleOffload (#2427)

2026-04-23 04:23:00 +08:00

frame_interpolation.md

[Feature] feat: add video frame interpolation postprocess (#2555)

2026-04-15 11:52:20 +08:00

lora.md

[Model] Adapt Wan2.2-I2V-A14B via LightX2V offline conversion path (#2134)

2026-04-13 14:20:04 +08:00

step_execution.md

[skip ci][Doc] Refine the Diffusion Features User Guide (#1928)

2026-03-30 14:28:04 +08:00