SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification (arXiv:2305.09781)

arXiv:2305.09781. SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification. By Xupeng Miao et al. Submitted 2023-05-16. Tree-based speculative inference and verification for accelerating LLM serving. 2026-10-10: Fetched https://arxiv.org/abs/2305.09781. Title: 'SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification'. Peer-reviewed venue confirmed: ASPLOS 2024. Abstract confirms tree-based speculative inference and verification for accelerating LLM serving.