Yue Yu

Hybrid LLM inference systems exploit both GPU and CPU for computation and memory but are bottlenecked by the CPU’s lower computational capabilities. Recent approaches leverage activation sparsity by offline partitioning FFN neurons into "hot" (frequently activated) and "cold" (rarely activated) s...

File synchronization (sync) based on Content-Defined Chunking (CDC) is gaining increasing importance for data migration over networks owing to its effectiveness in detecting and eliminating duplicate data within synchronized files. CDC-based sync schemes typically comprise three phases: file chun...

Optimizing the trade-off among predictive performance and computational cost is a central focus in the deployment of Large Language Models (LLMs). Current routing methods primarily rely on direct mapping from queries to models based on surface-level features, making them susceptible to the memori...

While large language models (LLMs) have made significant progress in expanding their context windows, they still face great challenges in effectively organizing and utilizing long-term memory to maintain conversation consistency and coherence. Summarizing historical conversations has achieved rem...