3 citations · 10 across the 21 of their papers we have counts for
22 papers
Divergent-Convergent Reasoning: Scaling Test-Time Compute through Structured Solution Synthesis
Bo Wen, Yuhao Chen, Erhan Bilal +3
Test-time compute can substantially improve Large Language Model (LLM) reasoning performance, yet how and when additional compute helps remains poorly understood. We study Divergen…
Learning Agent Execution for KV-Cache Management in Agentic Serving
Rui Zhang, Chaeeun Kim, Shaoting Feng +6
Multi-agent LLM systems have emerged as an important deployment paradigm for AI services, where each user request is decomposed into a sequence of specialized agents. Across these…
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…
VeriCache: Turning Lossy KV Cache into Lossless LLM Inference
Jiayi Yao, Samuel Shen, Kuntai Du +7
The large size of the KV cache has become a major bottleneck for serving LLMs with increasing context lengths. In response, many KV cache compression methods, such as token droppin…
The 1/W Law: An Analytical Study of Context-Length Routing Topology and GPU Generation Gains for LLM Inference Energy Efficiency
Huamin Chen, Xunzhuo Liu, Yuhan Liu +3
How many tokens can a GPU inference cluster deliver per watt? Across deployments of identical hardware, the answer varies by 40x -- not because of software inefficiency, but becaus…
Token-Budget-Aware Pool Routing for Cost-Efficient LLM Inference
Huamin Chen, Xunzhuo Liu, Junchen Jiang +2
Production vLLM fleets provision every instance for worst-case context length, wasting 4-8x concurrency on the 80-95% of requests that are short and simultaneously triggering KV-ca…
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…
FleetOpt: Analytical Fleet Provisioning for LLM Inference with Compress-and-Route as Implementation Mechanism
Huamin Chen, Xunzhuo Liu, Yuhan Liu +3
Modern LLM GPU fleets are provisioned for worst-case context lengths that the vast majority of requests never approach, wasting GPU capacity on idle KV-cache slots. We present Flee…
inference-fleet-sim: A Queueing-Theory-Grounded Fleet Capacity Planner for LLM Inference
Huamin Chen, Xunzhuo Liu, Yuhan Liu +3
Sizing a GPU fleet for LLM inference is harder than it looks. The obvious questions -- how many GPUs, which type, where to split a two-pool fleet -- have no closed-form answers. Th…
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…
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…
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…
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…
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…
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,…
Towards More Economical Context-Augmented LLM Generation by Reusing Stored KV Cache
Hanchen Li, Yuhan Liu, Yihua Cheng +2
Across large language model (LLM) applications, we observe an emerging trend for reusing KV caches to save the prefill delays of processing repeated input texts in different LLM in…
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…
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…
Automatic and Efficient Customization of Neural Networks for ML Applications
Yuhan Liu, Chengcheng Wan, Kuntai Du +4
ML APIs have greatly relieved application developers of the burden to design and train their own neural network models -- classifying objects in an image can now be as simple as on…
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,…
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…