WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More
This addresses deployment challenges for LLM users by reducing memory consumption, though it is incremental as it builds on existing quantization methods.
The paper tackles the high memory demands of Large Language Models by proposing WKVQuant, a quantization framework for weights and key/value cache, achieving nearly comparable memory savings to weight-activation quantization while approaching the performance of weight-only quantization.
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, we propose WKVQuant, a PTQ framework especially designed for quantizing weights and the key/value (KV) cache of LLMs. Specifically, we incorporates past-only quantization to improve the computation of attention. Additionally, we introduce two-dimensional quantization strategy to handle the distribution of KV cache, along with a cross-block reconstruction regularization for parameter optimization. Experiments show that WKVQuant achieves almost comparable memory savings to weight-activation quantization, while also approaching the performance of weight-only quantization.