5 papers
ToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decoding
Heming Xia, Yongqi Li, Cunxiao Du +2
Tool calling has greatly expanded the practical utility of large language models (LLMs) by enabling them to interact with external applications. As LLM capabilities advance, effect…
Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting
Heming Xia, Cunxiao Du, Rui Li +3
Large reasoning models (LRMs) have demonstrated remarkable proficiency in tackling complex tasks through step-by-step thinking. However, this lengthy reasoning process incurs subst…
SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
Heming Xia, Yongqi Li, Jun Zhang +2
Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality. It works by first employing a compact model to draft multi…
Tutorial Proposal: Speculative Decoding for Efficient LLM Inference
Heming Xia, Cunxiao Du, Yongqi Li +2
This tutorial presents a comprehensive introduction to Speculative Decoding (SD), an advanced technique for LLM inference acceleration that has garnered significant research intere…
Efficient Inference for Large Language Model-based Generative Recommendation
Xinyu Lin, Chaoqun Yang, Wenjie Wang +5
Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly particularly due to excessive inference latency caus…