AI Paper Atlas

Research map / Architectures and efficiency / Quantization

MPQ: A Message-Passing View of Post-Training Quantization

Yanshuo Chen, chenxi liu, Reza Shirkavand, Heng Huang

NeurIPS 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of LLMs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Casts row-wise post-training quantization as a message-passing problem so that weight blocks are not committed to a single codeword before neighboring blocks are considered.

Problem

Existing PTQ solvers (GPTQ, LDLQ, block coordinate descent) commit each weight block to a single codeword before its neighbors are considered, leaving near-optimal alternatives unexplored when compressing LLM weights to low-bit representations without retraining.

Approach

Recasts row-wise PTQ as a message-passing inference problem over weight blocks, so that multiple candidate codewords per block can be maintained and exchanged with neighbors instead of greedily fixing one per block.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace hard-decision greedy solvers with finite-temperature VAMP plus block CD (MPQ)Llama3-8B 2-bit E8P12 · WikiText-2perplexity: 12.76 -> 11.63 (vs LDLQ + CD)Improved
use MPQ instead of OJBKQ at 3-bit scalarLlama3-8B · WikiText-2perplexity: 7.95 -> 7.81Improved
use MPQ instead of OJBKQ at 4-bit scalarLlama3-8B · WikiText-2perplexity: 6.48 -> 6.46Improved
add 3 CD passes to greedy GPTQ (ablation)GPTQ 3-bit · WikiText-2perplexity: 8.29 -> 8.43 (Llama3-8B)No clear effect
add 3 CD passes to LDLQ (ablation)LDLQ 2-bit E8P12 · WikiText-2perplexity: 15.01 -> 12.76Improved
add AWQ scaling before RHT in MPQ (VAMP-only) (ablation)MPQ 3-bit scalar · WikiText-2perplexity: 31.24 -> 13.76 (Llama3.2-1B)Improved
add AWQ scaling before RHT in full MPQ (ablation)MPQ 3-bit scalar · WikiText-2perplexity: 8.09 -> 7.81 (Llama3-8B)Improved
add CD refinement after VAMP (3-bit scalar, 4 VAMP iterations) (ablation)MPQ 3-bit scalar · WikiText-2perplexity: 7.80 -> 7.88No clear effect
add CD refinement after VAMP at 2-bit E8P12 (16 VAMP iterations) (ablation)MPQ 2-bit E8P12 · WikiText-2perplexity: 17.24 -> 11.63Improved
increase VAMP iterations from 1 to 16 with 3 CD sweeps (ablation)MPQ 2-bit E8P12 · WikiText-2perplexity: 14.34 -> 11.63Improved
use MPQ initialization with D4 codebook instead of LDLQ (ablation)2-bit D4 codebook + CD3 · WikiText-2perplexity: 14.6389 -> 12.9658Improved
extend CD refinement of the LDLQ baseline to 20 sweeps (ablation)LDLQ 2-bit E8P12 · WikiText-2perplexity: 12.756 -> 12.651No clear effect

Experimental setup

Baselines: GPTQ LDLQ block coordinate descent

Builds on: GPTQ LDLQ block coordinate descent

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy