WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More

arXiv:2402.12065v1 Announce Type: new
Abstract: Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on the quantization of LLMs, a technique that reduces memory consumption by converting model parameters and activations into low-bit integers. We critically analyze the existing quantization approaches, identifying their limitations in balancing the accuracy and efficiency of the quantized LLMs. To advance beyond these limitations, …

abstract arxiv auto cache challenges computational consumption cs.ai cs.cl cs.lg deployment face key language language models large language large language models llms memory memory consumption paper process quantization requirements text text generation type value