kernels-community/quantization-gptq

This is the repository card of kernels-community/quantization-gptq that has been pushed on the Hub. It was built to be used with the kernels library. This card was automatically generated.

How to use

# make sure `kernels` is installed: `pip install -U kernels`
from kernels import get_kernel

kernel_module = get_kernel("kernels-community/quantization-gptq")
gemm_int4_forward = kernel_module.gemm_int4_forward

gemm_int4_forward(...)

Available functions

• gemm_int4_forward

Benchmarks

No benchmark available yet.