papers

Publications (10)

cs.LG2025

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…

cs.NI2024

Eloquent: A More Robust Transmission Scheme for LLM Token Streaming

Hanchen Li, Yuhan Liu, Yihua Cheng +3

To render each generated token in real-time for users, the Large Language Model (LLM) server generates tokens one by one and streams each token (or group of a few tokens) through t…

cs.NI2024

CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving

Yuhan Liu, Hanchen Li, Yihua Cheng +11

As large language models (LLMs) take on complex tasks, their inputs are supplemented with longer contexts that incorporate domain knowledge. Yet using long contexts is challenging,…

cs.NI2022

A new hope for network model generalization

Alexander Dietmüller, Siddhant Ray, Romain Jacob +1

Generalizing machine learning (ML) models for network traffic dynamics tends to be considered a lost cause. Hence for every new task, we design new models and train them on model-s…

cs.NI2026

An Internet for the KV Cache: Rethinking Classical Infrastructure Boundaries in the LLM Inference Age

Siddhant Ray, Nick Feamster, Junchen Jiang

LLM inference has become a global-scale, heterogeneous workload spanning agents, retrieval, tool-use, code execution and multi-modal reasoning. These workloads naturally enable con…

cs.MA2026

Argo: Efficient Importance Labeling for Enterprise Email Systems

Siddhant Ray, Ganesh Ananthanarayanan, Kevin Chian +5

Email importance labeling has long been a critical yet challenging problem for businesses and individuals. Traditional approaches; such as keyword matching, user-defined rules, and…

cs.OS2026

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…

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.NI2026

Characterizing the Impact of Active Queue Management on Speed Test Measurements

Siddhant Ray, Taveesh Sharma, Jonatas Marques +3

Present day speed test tools measure peak throughput, but often fail to capture the user-perceived responsiveness of a network connection under load. Recently, platforms such as ND…

cs.NI2026

SwiftQueue: Optimizing Low-Latency Applications with Swift Packet Queuing

Siddhant Ray, Xi Jiang, Jack Luo +2

Low Latency, Low Loss, and Scalable Throughput (L4S), as an emerging router-queue management technique, has seen steady deployment in the industry. An L4S-enabled router assigns ea…