kernels-community
/

quantization-eetq

Model card Files Files and versions

quantization-eetq / build /torch211-cxx11-cu128-x86_64-linux /__init__.py

danieldk's picture

danieldk HF Staff

Build uploaded using `kernels`.

504012d verified about 2 months ago

history blame contribute delete

167 Bytes

	from .custom_ops import w8_a16_gemm, w8_a16_gemm_, preprocess_weights, quant_weights

	__all__ = ["w8_a16_gemm", "w8_a16_gemm_", "preprocess_weights", "quant_weights"]