paper-with-me

Papers

NestQuant: Nested Lattice Quantization for Matrix Products and LLMs

2025-02-13 · Semyon Savkin, Eitan Porat, Or Ordentlich, Yury Polyanskiy

Post-training quantization (PTQ) has emerged as a critical technique for efficient deployment of large language models (LLMs). This work proposes NestQuant, a novel PTQ scheme for weights and activations that is based on self-similar nested lattices. Recent works have mathematically shown such quantizers to be information-theoretically optimal for low-precision matrix multiplication. We implement a practical low-complexity version of NestQuant based on Gosset lattice, making it a drop-in quantizer for any matrix multiplication step (e.g., in self-attention, MLP etc). For example, NestQuant quantizes weights, KV-cache, and activations of Llama-3-8B to 4 bits, achieving perplexity of 6.6 on wikitext2. This represents more than 55% reduction in perplexity gap with respect to unquantized model (perplexity of 6.14) compared to state-of-the-art Metas SpinQuant (perplexity 7.3), OstQuant (7.3) and QuaRot (8.2). Comparisons on bigger models (up to 70B) and on various LLM evaluation benchmarks confirm uniform superiority of NestQuant.

📄 PDF Abstract BibTeX arXiv:2502.09720

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

NestQuant: Post-Training Integer-Nesting Quantization for On-Device DNN

2025-06-22 · Jianhang Xie, Chuntao Ding, Xiaqing Li, Shenyuan Ren 외

Deploying quantized deep neural network (DNN) models with resource adaptation capabilities on ubiquitous Internet of Things (IoT) devices to provide high-quality AI services can leverage the benefits of compression and m…

Quantization

Optimal Quantization for Matrix Multiplication

2024-10-17 · Or Ordentlich, Yury Polyanskiy

Recent work in machine learning community proposed multiple methods for performing lossy compression (quantization) of large matrices. This quantization is important for accelerating matrix multiplication (main component…

Quantization

Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression

2025-10-23 · Xi Zhang, Xiaolin Wu, Jiamang Wang, Weisi Lin arxiv

Large Language Models (LLMs) have demonstrated remarkable capabilities but typically require extensive computational resources and memory for inference. Post-training quantization (PTQ) can effectively reduce these deman…

Gradient Based Method for the Fusion of Lattice Quantizers

2025-02-09 · Liyuan Zhang, Hanzhong Cao, Jiaheng Li, Minyang Yu

In practical applications, lattice quantizers leverage discrete lattice points to approximate arbitrary points in the lattice. An effective lattice quantizer significantly enhances both the accuracy and efficiency of the…

Quantization

HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models

2026-06-22 · Yuval Domb, Hadar Sackstein, Tomer Solberg arxiv

We present HyperQuant (Hadamard, optimallY Packing, Entropy Rice-coding), a unified post-training quantization pipeline for the weights and the KV cache of large language and diffusion transformers. Across a suite of sel…