Sayak Paul 2432f80ca3 [LoRA] feat: support loading loras into 4bit quantized Flux models. (#10578) ...

* feat: support loading loras into 4bit quantized models.

* updates

* update

* remove weight check.

2025-01-15 12:40:40 +05:30

..

bnb

[LoRA] feat: support loading loras into 4bit quantized Flux models. (#10578)

2025-01-15 12:40:40 +05:30

gguf

Add AuraFlow GGUF support (#10463)

2025-01-08 13:23:12 +05:30

torchao

Test sequential cpu offload for torchao quantization (#10506)

2025-01-14 09:54:06 +05:30