Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding
Heming Xia, Zhe Yang, Qingxiu Dong, Peiyi Wang, Yongqi Li, Tao Ge, Tianyu Liu, Wenjie Li and 1 more
Who it is from
- Microsoft Research Asiaaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- CMMLU: Measuring massive multitask language understanding in ChineseMicrosoft Research Asia · 685 citations
- Fine-Tuning LLaMA for Multi-Stage Text RetrievalMicrosoft Research Asia · 540 citations
- EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time TestMicrosoft Research Asia · 465 citations
- Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement LearningMicrosoft Research Asia · 430 citations
- NaturalSpeech : End-to-End Text-to-Speech Synthesis With Human-Level QualityMicrosoft Research Asia · 425 citations
- A Survey on Video Diffusion ModelsMicrosoft Research Asia · 390 citations