RedHatAI
/

quantization

Model card Files Files and versions

quantization / ext-torch

14.6 kB

Ctrl+K

Ctrl+K

2 contributors

History: 2 commits

danieldk's picture

danieldk HF Staff

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

5c6fb68 over 1 year ago

__init__.py

6.07 kB
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm` over 1 year ago
torch_binding.cpp

6.26 kB
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm` over 1 year ago
torch_binding.h

2.28 kB
Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm` over 1 year ago