9 papers
Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving
Rui Li, Zhaoning Zhang, Libo Zhang +3
Speculative decoding (SD) accelerates LLM inference by verifying draft tokens in parallel. However, this method presents a critical trade-off: it improves throughput in low-load, m…
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators
Jonathan Li, Nasim Farahini, Evgenii Iuliugin +19
The proliferation of 100B+ parameter Large Language Models (LLMs) with 100k+ context length support have resulted in increasing demands for on-chip memory to support large KV cache…
Speculative Decoding with a Speculative Vocabulary
Miles Williams, Young D. Kwon, Rui Li +2
Speculative decoding has rapidly emerged as a leading approach for accelerating language model (LM) inference, as it offers substantial speedups while yielding identical outputs. T…
Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning
Yiqun Chen, Jinyuan Feng, Wei Yang +9
The inference overhead induced by redundant reasoning undermines the interactive experience and severely bottlenecks the deployment of Large Reasoning Models. Existing reinforcemen…
BootSeer: Analyzing and Mitigating Initialization Bottlenecks in Large-Scale LLM Training
Rui Li, Xiaoyun Zhi, Jinxin Chi +14
Large Language Models (LLMs) have become a cornerstone of modern AI, driving breakthroughs in natural language processing and expanding into multimodal jobs involving images, audio…
LogicCat: A Chain-of-Thought Text-to-SQL Benchmark for Complex Reasoning
Tao Liu, Xutao Mao, Hongying Zan +12
Text-to-SQL is a critical task in natural language processing that aims to transform natural language questions into accurate and executable SQL queries. In real-world scenarios, t…