We present ongoing work on a new automatic code generation approach for supporting quantized generative inference on LLMs such as LLaMA or OPT on off-the-shelf CPUs. Our approach is informed by the target architecture and a performance model, including both hardware characteristics and method-specific accuracy constraints. Results on CPU-based inference for LLaMA models show that our approach can lead to high performance and high accuracy, comparing favorably to the best existing open-source solution. A preliminary implementation is available at https://github.com/IST-DASLab/QIGen.
@article{arxiv.2307.03738,
title = {QIGen: Generating Efficient Kernels for Quantized Inference on Large Language Models},
author = {Tommaso Pegolotti and Elias Frantar and Dan Alistarh and Markus Püschel},
journal= {arXiv preprint arXiv:2307.03738},
year = {2023}
}