ooooooye 823af92347 [Bugfix][Ascend NPU][Diffusion] Load over-wide unquantized fallback weights straight into host memory under DLOFix/mxfp online offload after quant (#7009) ...

Signed-off-by: brandneway <gyuan4892@gmail.com>

2026-09-18 07:36:48 +00:00

..

checkpoint_adapters

[Refactor][Diffusion] Remove model-specific names from LoRA and ModelOpt loader defaults (#5907)

2026-09-12 20:30:03 +08:00

host_weights

[Diffusion] Register HWR mmap for direct DLO H2D (#6591)

2026-08-25 23:30:11 +08:00

__init__.py

[Diffusion] Refactor diffusion models weights loading (#157)

2025-12-06 11:12:13 +00:00

diffusers_loader.py

[Bugfix][Ascend NPU][Diffusion] Load over-wide unquantized fallback weights straight into host memory under DLOFix/mxfp online offload after quant (#7009)

2026-09-18 07:36:48 +00:00

host_weight_loader.py

[Diffusion] Register HWR mmap for direct DLO H2D (#6591)

2026-08-25 23:30:11 +08:00

host_weight_plan.py

[Perf][Diffusion] Optimize HSDP startup via Rank-0 shared weight loading and accelerated LoRA delta computation (#7005)

2026-09-11 08:28:42 +00:00

hub_prefetch.py

Add vLLM-Omni library info to Hugging Face Hub requests (#5381)

2026-09-08 10:08:38 -06:00