8 citations · 21 across the 15 of their papers we have counts for
16 papers
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…
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…
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…
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…
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…
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…
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…
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…
GRACE: Loss-Resilient Real-Time Video through Neural Codecs
Yihua Cheng, Ziyi Zhang, Hanchen Li +9
In real-time video communication, retransmitting lost packets over high-latency networks is not viable due to strict latency requirements. To counter packet losses without retransm…