Saved in:
Bibliographic Details
Main Authors: Zhou, Jiahao, Lin, Chengliang, Li, Dingji, Dong, Mingkai, Chen, Haibo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.15620
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914415583952896
author Zhou, Jiahao
Lin, Chengliang
Li, Dingji
Dong, Mingkai
Chen, Haibo
author_facet Zhou, Jiahao
Lin, Chengliang
Li, Dingji
Dong, Mingkai
Chen, Haibo
contents Semantic top-K selection with cross-encoder rerankers underpins on-device AI services, such as retrieval-augmented generation, agent memory, and personalized recommendation. However, its latency and memory demands dominate end-to-end budgets on edge hardware. Revisiting the objective of top-K selection, we reveal that only relative rankings matter, not exact per-candidate scores. We further observe sequence-level sparsity: relative rankings progressively stabilize in intermediate layers, enabling early pruning prior to completing full inference. Building on this insight, we propose monolithic forwarding and develop a training-free inference system, PRISM. By maintaining a global view of all candidates, it reduces latency through progressive cluster pruning. It also bounds peak memory usage by strategically overlapping I/O with computation via overlapped layer streaming and chunked execution. We evaluate PRISM against state-of-the-art baselines on rerankers from 0.6 B to 8 B parameters across Apple M2 and RTX 5070. PRISM consistently reduces latency by up to 89.2% and peak memory by up to 91.3% in microbenchmarks, without compromising precision. Across three real-world on-device AI applications, PRISM lowers latency by 11.6%-51.0% and peak memory by 18.6%-77.8%, demonstrating substantial improvements in efficiency and deployability.
format Preprint
id arxiv_https___arxiv_org_abs_2510_15620
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwarding
Zhou, Jiahao
Lin, Chengliang
Li, Dingji
Dong, Mingkai
Chen, Haibo
Machine Learning
Semantic top-K selection with cross-encoder rerankers underpins on-device AI services, such as retrieval-augmented generation, agent memory, and personalized recommendation. However, its latency and memory demands dominate end-to-end budgets on edge hardware. Revisiting the objective of top-K selection, we reveal that only relative rankings matter, not exact per-candidate scores. We further observe sequence-level sparsity: relative rankings progressively stabilize in intermediate layers, enabling early pruning prior to completing full inference. Building on this insight, we propose monolithic forwarding and develop a training-free inference system, PRISM. By maintaining a global view of all candidates, it reduces latency through progressive cluster pruning. It also bounds peak memory usage by strategically overlapping I/O with computation via overlapped layer streaming and chunked execution. We evaluate PRISM against state-of-the-art baselines on rerankers from 0.6 B to 8 B parameters across Apple M2 and RTX 5070. PRISM consistently reduces latency by up to 89.2% and peak memory by up to 91.3% in microbenchmarks, without compromising precision. Across three real-world on-device AI applications, PRISM lowers latency by 11.6%-51.0% and peak memory by 18.6%-77.8%, demonstrating substantial improvements in efficiency and deployability.
title On-device Semantic Selection Made Low Latency and Memory Efficient with Monolithic Forwarding
topic Machine Learning
url https://arxiv.org/abs/2510.15620