activity
20242026
collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project

Huamin Chen, Xunzhuo Liu, Bowei He +5

Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing, context-length pool routing, rout…

cs.LG2026

Outcome-Aware Tool Selection for Semantic Routers: Latency-Constrained Learning Without LLM Inference

Huamin Chen, Xunzhuo Liu, Junchen Jiang +2

Semantic routers in LLM inference gateways select tools in the critical request path, where every millisecond of added latency compounds across millions of requests. We propose Out…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2024

OneAdapt: Fast Configuration Adaptation for Video Analytics Applications via Backpropagation

Kuntai Du, Yuhan Liu, Yitian Hao +5

Deep learning inference on streaming media data, such as object detection in video or LiDAR feeds and text extraction from audio waves, is now ubiquitous. To achieve high inference…

cs.LG2024

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…