Robust Parameter-Efficient LLM Adaptation on Analog Hardware

arXiv:2610.05318v1 Announce Type: new Abstract: Analog in-memory computing is a promising platform for on-device execution of large language models because it performs matrix--vector multiplications (MVMs) in memory and in parallel, reducing data movement. However, limited digital-to-analog converter precision, input noise, and finite conductance states can degrade model accuracy, while full-model retraining to address these effects can be costly. We develop an optimizer-agnostic, parameter-efficient adaptation method based on Low-Rank Adaptation (LoRA), keeping the pretrained weights stored on analog arrays fixed while training the LoRA weights to adapt to downstream tasks and hardware non-idealities. Reliable adaptation requires handling errors in both forward and backward MVMs and physical weight updates. We use input reshaping to reduce input-induced MVM errors and update accumulation to retain small updates before programming them to finite-state analog devices. Across Llama-3.2-1B-Instruct and Llama-3-8B with both Muon and AdamW, input reshaping improves analog LoRA fine-tuning under noisy MVM computation. Update accumulation separately preserves sub-threshold updates and substantially improves adaptation under finite-resolution programming, including configurations with as few as 20 conductance states. Additional experiments show consistent held-out negative log-likelihood improvements across noisy analog settings.

Related

• MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation
• LoRAQuant: Mixed-Precision Quantization of LoRA to Ultra-Low Bits
• BoHA: Blockwise Hadamard Product Adaptation for Parameter-Efficient Fine-Tuning
• Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation

Source: arXiv cs.LG | 2026-10-06