7 papers · 1 filter
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…
LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference
Yuhan Liu, Yihua Cheng, Jiayi Yao +8
KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV cach…
When to Reason: Semantic Router for vLLM
Chen Wang, Xunzhuo Liu, Yuhan Liu +4
Large Language Models (LLMs) demonstrate substantial accuracy gains when augmented with reasoning modes such as chain-of-thought and inference-time scaling. However, reasoning also…
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…
PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications
Kuntai Du, Bowen Wang, Chen Zhang +9
Besides typical generative applications, like ChatGPT, GitHub Copilot, and Cursor, we observe an emerging trend that LLMs are increasingly used in traditional discriminative tasks,…
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
Jiayi Yao, Hanchen Li, Yuhan Liu +6
Large language models (LLMs) often incorporate multiple text chunks in their inputs to provide the necessary contexts. To speed up the prefill of the long LLM inputs, one can pre-c…