kernels-community
/

quantization

Model card Files Files and versions Community

quantization / compressed_tensors

2 contributors

History: 1 commit

danieldk's picture

danieldk HF staff

Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`

5c6fb68 4 months ago

int8_quant_kernels.cu

10.4 kB

Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm` 4 months ago