Hugging Face's logo

RedHatAI
/
quantization

kernel
Model card Files
xet
 Community
3
quantization / ext-torch /torch_binding.cpp

Commit History

  1. Add full Marlin support and tests for Marlin/CUTLASS

    danieldk HF Staff
    165b25c

  1. Add GPTQ-Marlin

    danieldk HF Staff
    c31b5ce

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

    danieldk HF Staff
    5c6fb68

  2. Add cutlass_w8a8

    danieldk HF Staff
    b4cad21