Elias Frantar (elias.frantar@ist.ac.at) — original author of the Marlin
  W4A16 GEMM kernel (IST-DASLab, Institute of Science and Technology
  Austria).

The paper:

  MARLIN: Mixed-Precision Auto-Regressive Parallel Inference of
  Large Language Models
  Elias Frantar, Roberto L. Castro, Jiale Chen, Torsten Hoefler,
  Dan Alistarh
  arXiv:2408.11743

  https://arxiv.org/abs/2408.11743

Upstream repository: https://github.com/IST-DASLab/marlin
