5 papers
EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving
Shaoting Feng, Yuhan Liu, Hanchen Li +11
Reusing KV cache is essential for high efficiency of Large Language Model (LLM) inference systems. With more LLM users, the KV cache footprint can easily exceed GPU memory capacity…
AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving
Shaoting Feng, Hanchen Li, Kuntai Du +8
Large language model (LLM) applications often reuse previously processed context, such as chat history and documents, which introduces significant redundant computation. Existing L…
METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation
Siddhant Ray, Rui Pan, Zhuohan Gu +5
RAG (Retrieval Augmented Generation) allows LLMs (large language models) to generate better responses with external knowledge, but using more external knowledge often improves gene…
LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts
Zhuohan Gu, Jiayi Yao, Kuntai Du +1
As large language models (LLMs) show impressive performance on complex tasks, they still struggle with longer contextual understanding and high computational costs. To balance effi…
DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving
Yuhan Liu, Yuyang Huang, Jiayi Yao +9
Compound AI systems, such as agentic systems, are an emerging trend in large-scale enterprise settings, with multiple LLMs specialized for different users, tasks, and/or roles work…