RedHatAI
/

quantization

Model card Files Files and versions

quantization / gptq_marlin

4.26 kB

2 contributors

History: 1 commit

danieldk's picture

danieldk HF Staff

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

5c6fb68 about 1 year ago

marlin.cuh

2.27 kB

Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm` about 1 year ago
marlin_dtypes.cuh

1.99 kB

Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm` about 1 year ago