3 accepted papers
Weight-only quantization has become a standard approach for efficiently serving large language models (LLMs). However, existing methods fail to efficiently compress models to binary (1-bit), as they either require large amounts of data and compute or incur additional storage. In this work, we propos…
Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a critical trade-off between low-bit efficiency and performance. Residual binarization promises hardware-friendly, matmul-free inference by stacking binary ($\pm$1) layers, but is plagued by pathological feat…
Deploying large language models (LLMs) often faces challenges from substantial memory and computational costs. Quantization offers a solution, yet performance degradation in the sub-1-bit regime remains particularly difficult. This paper introduces LittleBit, a novel method for extreme LLM compressi…