QMC: Efficient SLM Edge Inference via Outlier-Aware Quantization and Emergent Memories Co-Design

TL;DR

QMC introduces a hybrid memory and outlier-aware quantization approach for small language models, significantly improving efficiency and deployment viability on edge devices by reducing memory, energy, and latency.

Contribution

The paper presents a novel retraining-free quantization method combined with a heterogeneous memory architecture tailored for SLM inference on edge platforms.

Findings

QMC reduces memory usage by up to 7.3x.

QMC decreases energy consumption by 11.7x.

QMC achieves 12.5x lower latency compared to FP16.

Abstract

Deploying Small Language Models (SLMs) on edge platforms is critical for real-time, privacy-sensitive generative AI, yet constrained by memory, latency, and energy budgets. Quantization reduces model size and cost but suffers from device noise in emerging non-volatile memories, while conventional memory hierarchies further limit efficiency. SRAM provides fast access but has low density, DRAM must simultaneously accommodate static weights and dynamic KV caches, which creates bandwidth contention, and Flash, although dense, is primarily used for initialization and remains inactive during inference. These limitations highlight the need for hybrid memory organizations tailored to LLM inference. We propose Outlier-aware Quantization with Memory Co-design (QMC), a retraining-free quantization with a novel heterogeneous memory architecture. QMC identifies inlier and outlier weights in SLMs, storing inlier weights in compact multi-level Resistive-RAM (ReRAM) while preserving critical outliers in high-precision on-chip Magnetoresistive-RAM (MRAM), mitigating noise-induced degradation. On language modeling and reasoning benchmarks, QMC outperforms and matches state-of-the-art quantization methods using advanced algorithms and hybrid data formats, while achieving greater compression under both algorithm-only evaluation and realistic deployment settings. Specifically, compared against SoTA quantization methods on the latest edge AI platform, QMC reduces memory usage by 6.3x-7.3x, external data transfers by 7.6x, energy by 11.7x, and latency by 12.5x when compared to FP16, establishing QMC as a scalable, deployment-ready co-design for efficient on-device inference.