5 papers
EndPrompt: Efficient Long-Context Extension via Terminal Anchoring
Han Tian, Luxuan Chen, Xinran Chen +10
Extending the context window of large language models typically requires training on sequences at the target length, incurring quadratic memory and computational costs that make lo…
Multi-stage Flow Scheduling for LLM Serving
Yijun Sun, Xudong Liao, Songrun Xie +5
Meeting stringent Time-To-First-Token (TTFT) requirements is crucial for LLM applications. To improve efficiency, modern LLM serving systems adopt disaggregated architectures with…
Analyzing Communication Predictability in LLM Training
Wenxue Li, Xiangzhou Liu, Yuxuan Li +9
Effective communication is essential in distributed training, with predictability being one of its most significant characteristics. However, existing studies primarily focus on ex…
Exploiting Student Parallelism for Efficient GPU Inference of BERT-like Models in Online Services
Weiyan Wang, Yilun Jin, Yiming Zhang +7
Due to high accuracy, BERT-like models have been widely adopted by text mining and web searching. However, large BERT-like models suffer from inefficient online inference, facing t…
DH-RAG: A Dynamic Historical Context-Powered Retrieval-Augmented Generation Method for Multi-Turn Dialogue
Feiyuan Zhang, Dezhi Zhu, James Ming +6
Retrieval-Augmented Generation (RAG) systems have shown substantial benefits in applications such as question answering and multi-turn dialogue \citep{lewis2020retrieval}. However,…