LASER: Load-Aware Serving with Early-Exit for Reasoning LLMs at the Edge
For edge deployment of reasoning LLMs, this work improves serving efficiency under load fluctuations, though the gains are incremental over fixed-threshold baselines.
LASER addresses the conflict between long chain-of-thought sequences in reasoning LLMs and constrained edge resources by introducing load-aware early exit thresholds and difficulty-aware budget pre-allocation, reducing average latency by 17-38% and improving SLO satisfaction by 3-6% with only 1% accuracy loss.
Large reasoning models (LRMs) such as DeepSeek-R1 have achieved strong performance through extended chain-of-thought (CoT) generation. However, deploying them on edge devices raises a conflict between long CoT sequences and constrained resources. Recent confidence-based early exit methods reduce CoT length for individual requests, yet they apply fixed thresholds from a single-request perspective, ignoring multi-request concurrency and load fluctuation in edge serving. To bridge this gap, we propose \underline{L}oad-\underline{A}ware \underline{S}erving with \underline{E}arly-exit for \underline{R}easoning (LASER). LASER couples two complementary designs: (1) a load-aware adaptive exit threshold that adjusts the confidence bar based on real-time system load within an empirically validated robust range, and (2) a difficulty- and load-aware reasoning budget pre-allocation that assigns compute resources by request difficulty and system capacity. We formulate the problem as a joint optimization of reasoning quality and service latency. Experiments on two reasoning models, four benchmarks, and diverse load conditions show that LASER reduces average latency by 17--38\% and improves service-level objective (SLO) satisfaction by 3--6\% over fixed-threshold baselines, at an average accuracy cost of only 1\%.