Skip to content
AI Atlas
PaperActive

RDQ: Residual Distribution Quantization for Large Language Models

arxiv.org/abs/2607.10137

quality89

Updated 4 h ago · first seen 11 Sept 2026

paper_01M294FSB4AVGHSJC1QE0GXQJV

Published
11 Sept 2026
T1 · 4 h ago
arXiv
2607.10137
T1 · 4 h ago
Category
cs.LG
T1 · 4 h ago

Abstract

Post-training quantization (PTQ) of large language models degrades sharply below 4-bit precision. We identify the root cause as residual stream distributional drift: quantization noise injected at each transformer layer accumulates in the shared residual representation, causing KL divergence from the FP16 baseline to grow super-linearly with depth (Pearson r=0.999 with log-perplexity, p<0.001, confirmed across all tested methods and bit-widths). We discover that 84% of LLaMA-3-8B layers exhibit non-Gaussian residual distributions (KS test, p<=0.05), and that per-layer residual stream variance grows 6,548x across depth. We propose RDQ (Residual Distribution Quantization), a PTQ framework whose central contribution is Cascaded Error Compensation (CEC): a sequential calibration procedure that captures the actual drifted activations each layer receives (computed by running calibration data through already-quantized upstream layers) and fits per-channel AWQ-style scales against those drifted inputs, with scales folded into preceding RMSNorm weights for exact mathematical equivalence at zero inference overhead. RDQ achieves state-of-the-art results on all three tested architectures: LLaMA-3-8B: 7.55 / 5.62 PPL (W3/W4); Qwen-2.5-7B: 7.46 / 6.38 PPL; Mistral-7B: 6.88 / 5.73 PPL. RDQ beats the best published baseline (LeanQuant/SpinQuant) at every model and bit-width combination, with gains up to -46.4% vs. RTN at W3A16 on LLaMA-3-8B. All output is standard group-128 asymmetric quantization, deployable on Qualcomm AIMET, GGUF, and any standard inference stack at zero runtime overhead.

Authors 1

Prateek Singh

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 4 h agohigh

Arxiv announce type
replace

Source:arXiv (Atom API + RSS)T1observed 4 h agohigh

arXiv id
2607.10137

Source:arXiv (Atom API + RSS)T1observed 4 h agohigh

Categories
cs.LG

Source:arXiv (Atom API + RSS)T1observed 4 h agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 4 h agohigh

Primary category
cs.LG

Source:arXiv (Atom API + RSS)T1observed 4 h agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 4 h agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

4 h ago

Conflicts

None