aiqbench analysis
SelectInfer addresses the critical bottleneck of deploying large language models on edge devices by introducing neuron-level optimizations rather than relying on traditional coarse-grained pruning. This approach dynamically loads and computes only the most relevant neurons at runtime, significantly reducing memory footprint and computational load while preserving task accuracy without requiring retraining. The work represents a meaningful advancement in making high-capability LLMs viable for resource-constrained environments through efficient inference architectures.
SelectInfer: Selective Neuron Loading and Computation for On-Device LLMs
arXiv:2607.18081v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across a range of Natural Language Processing (NLP) tasks, but their high computational and memory demands pose significant challenges for deployment on resource-constrained edge devices. Existing approaches to model compression and optimization often rely on coarse-grained pruning or quantization, which can compromise accuracy or require re-training and fine-tuning. In this work, we introduce SelectInfer, a neuron-level optimization framework that enables efficient LLM inference on edge devices through selective neuron loading and computation. By profiling and identifying both task-specific and general-purpose neurons using an offline LLM profiler, SelectInfer implements two key optimizations: selective loading, which reduces memory footprint by selectively loading a subset of neurons that were identified to be most important during the offline stage, and selective computation, which dynamically computes only the most relevant neurons at runtime. Evaluation across multiple datasets shows that SelectInfer achieves significant reductions in memory footprint and computation while preserving task performance, making it a practical step towards enabling LLM deployment on edge devices
Abstract:Large Language Models (LLMs) have demonstrated remarkable capabilities across a range of Natural Language Processing (NLP) tasks, but their high computational and memory demands pose significant challenges for deployment on resource-constrained edge devices. Existing approaches to model compression and optimization often rely on coarse-grained pruning or quantization, which can compromise accuracy or require re-training and fine-tuning. In this work, we introduce SelectInfer, a neuron-level optimization framework that enables efficient LLM inference on edge devices through selective neuron loading and computation. By profiling and identifying both task-specific and general-purpose neurons using an offline LLM profiler, SelectInfer implements two key optimizations: selective loading, which reduces memory footprint by selectively loading a subset of neurons that were identified to be most important during the offline stage, and selective computation, which dynamically computes only the most relevant neurons at runtime. Evaluation across multiple datasets shows that SelectInfer achieves significant reductions in memory footprint and computation while preserving task performance, making it a practical step towards enabling LLM deployment on edge devices
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2607.18081 [cs.LG]
(or arXiv:2607.18081v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.18081 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 264 words
Related coverage
Quantization and Pruning Methods to Make Your LLM Leaner
KDnuggets · Aug 28, 2026
Stop hand-tuning kernels: How Neuron Agentic Development accelerates AWS Trainium optimizations
AWS · Jun 10, 2026
[AINews] The Future of Latent Space
Latent Space · Sep 25, 2026
[AINews] Opus 5.5 is good at explainer videos
Latent Space · Sep 29, 2026