Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs

Abstract

As the rapid scaling of large language models (LLMs) poses significant challenges for deployment on resource-constrained devices, there is growing interest in extremely low-bit quantization, such as 2-bit. Although prior works have shown that 2-bit large models are pareto-optimal over their 4-bit smaller counterparts in both accuracy and latency, these advancements have been limited to pre-trained LLMs and have not yet been extended to instruction-tuned models. To bridge this gap, we propose Unified Progressive Quantization (UPQ)$-$a novel progressive quantization framework (FP16$\rightarrow$INT4$\rightarrow$INT2) that unifies block-wise post-training quantization (PTQ) with distillation-based quantization-aware training (Distill-QAT) for INT2 instruction-tuned LLM quantization. UPQ first quantizes FP16 instruction-tuned models to INT4 using block-wise PTQ to significantly reduce the quantization error introduced by subsequent INT2 quantization. Next, UPQ applies Distill-QAT to enable INT2 instruction-tuned LLMs to generate responses consistent with their original FP16 counterparts by minimizing the generalized Jensen-Shannon divergence (JSD) between the two. To the best of our knowledge, we are the first to demonstrate that UPQ can quantize open-source instruction-tuned LLMs to INT2 without relying on proprietary post-training data, while achieving state-of-the-art performances on MMLU and IFEval$-$two of the most representative benchmarks for evaluating instruction-tuned LLMs.