Hugging Face's logo

RedHatAI
/
quantization

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

Commit History

  1. Adjust for latest kernel-builder changes

    danieldk HF Staff
    f44baaa

  1. Expose ops (handy for tests etc.)

    danieldk HF Staff
    e3a7455

  1. Build

    danieldk HF Staff
    a6c77d7

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

    danieldk HF Staff
    165b25c

  1. Import CUTLASS tests and add missing scaled mm with zp signature

    danieldk HF Staff
    2dd62c9

  2. 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