quantization / ext-torch

Commit History

Expose ops (handy for tests etc.)
e3a7455

danieldk HF Staff commited on

Build
a6c77d7

danieldk HF Staff commited on

Add full Marlin support and tests for Marlin/CUTLASS
165b25c

danieldk HF Staff commited on

Import CUTLASS tests and add missing scaled mm with zp signature
2dd62c9

danieldk HF Staff commited on

Add GPTQ-Marlin
c31b5ce

danieldk HF Staff commited on

Add `scaled_(int|fp8)_quant` and `fp8_marlin_gemm`
5c6fb68

danieldk HF Staff commited on

Add cutlass_w8a8
b4cad21

danieldk HF Staff commited on