← Search

Maximilian L. Croci

2 accepted papers

2024

QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

NeurIPS 2024poster

We introduce QuaRot, a new Quantization scheme based on Rotations, which is able to quantize LLMs end-to-end, including all weights, activations, and KV cache in 4 bits. QuaRot rotates LLMs in a way that removes outliers from the hidden state without changing the output, making quantization easier.…

2024

SliceGPT: Compress Large Language Models by Deleting Rows and Columns

ICLR 2024poster

Large language models have become the cornerstone of natural language processing, but their use comes with substantial costs in terms of compute and memory resources. Sparsification provides a solution to alleviate these resource constraints, and recent works have shown that trained models can be sp…