UniSpec: Training-Free Speculative Decoding for Robust LLM Acceleration Across Languages and Hardware
Truong Dinh Do, Nguyen-Khang Le Japan Advanced Institute of Science and Technology, Tokyo Institute of Technology, Le-Minh Nguyen Japan Advanced Institute of Science and Technology, Tokyo Institute of Technology
Speculative decoding accelerates large language model (LLM) inference through a draft-and-verify paradigm, yet existing methods face three key limitations: reliance on fixed draft templates that ignore device-specific verification costs, lack of mechanisms to assess draft token quality, and suboptimal tree expansion strategies. We introduce UniSpec, a training-free, lossless speculative decoding framework that enables robust, plug-and-play LLM acceleration across diverse hardware configurations and languages. UniSpec incorporates three novel components: (1) a device-aware calibration mechanism that determines the optimal draft size by measuring the acceptance-time trade-off on each target device; (2) a confidence score estimation module that assigns quality scores to n-grams based on the verifier’s token probabilities, enabling selective retention of high-quality draft candidates; and (3) an improved tree expansion strategy that broadens first-level exploration and applies threshold-based filtering to prune low-confidence nodes. To comprehensively evaluate multilingual performance, we create a comprehensive benchmark, covering seven languages across seven generation tasks. Experiments with various LLM architectures, hardware environments, and languages demonstrate that UniSpec consistently outperforms existing training-free methods, achieving speedups of up to 2.6x while maintaining output quality identical to standard autoregressive decoding. Our code and benchmark are publicly available.
尚无 AI 解读，展示原文摘要
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表