kernels-community
/

quantization-bitsandbytes

Model card Files Files and versions

quantization-bitsandbytes / build /torch29-cxx11-cpu-x86_64-linux /__init__.py

danieldk's picture

danieldk HF Staff

Build uploaded using `kernels`.

be136a5 verified 16 days ago

history blame contribute delete

74 Bytes

	from .custom_ops import gemm_4bit_forward

	__all__ = ["gemm_4bit_forward"]