KD

Kuntai Du

0000-0002-3964-4079

cs.LGcs.NIcs.AIcs.DCcs.CLcs.MMcs.ARcs.CVcs.IRcs.OS

On Valency

published · living versions

Gandalf: Flash Shall Not Die! Increasing Flash Storage Lifetime for KV Cache Offloading in LLM Serving

with Maharani A. P. Irawan, Jiayi Yao, Dongjoo Seo, Yuyang Huang +2

1 version

W_pfe6ens3v1 · current

Preprints & journals

18 papers in the corpus · 2022–2026

Gandalf: Flash Shall Not Die! Increasing Flash Storage Lifetime for KV Cache Offloading in LLM Serving

Maharani A. P. Irawan, Kuntai Du, Jiayi Yao et al.

0 citations

2610.30791v12026arXiv

Learning Agent Execution for KV-Cache Management in Agentic Serving

Rui Zhang, Chaeeun Kim, Shaoting Feng et al.

0 citations

2608.14624v12026arXiv

VeriCache: Turning Lossy KV Cache into Lossless LLM Inference

Jiayi Yao, Samuel Shen, Kuntai Du et al.

0 citations

2605.17613v12026arXiv

LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference

Yuhan Liu, Yihua Cheng, Jiayi Yao et al.

2 citations

2510.09665v22025arXiv

AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving

Shaoting Feng, Hanchen Li, Kuntai Du et al.

0 citations

2509.00105v22025arXiv

PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications

Kuntai Du, Bowen Wang, Chen Zhang et al.

12 citations

2505.07203v12025arXiv

Jenga: Effective Memory Management for Serving LLM with Heterogeneity

Chen Zhang, Kuntai Du, Shu Liu et al.

6 citations

2503.18292v12025arXiv

Towards More Economical Context-Augmented LLM Generation by Reusing Stored KV Cache

Hanchen Li, Yuhan Liu, Yihua Cheng et al.

2 citations

2503.14647v12025arXiv

METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation

Siddhant Ray, Rui Pan, Zhuohan Gu et al.

9 citations

2412.10543v32024arXiv

LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts

Zhuohan Gu, Jiayi Yao, Kuntai Du et al.

0 citations

2411.13009v22024arXiv

Do Large Language Models Need a Content Delivery Network?

Yihua Cheng, Kuntai Du, Jiayi Yao et al.

1 citation

2409.13761v22024arXiv

CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion

Jiayi Yao, Hanchen Li, Yuhan Liu et al.

76 citations

2405.16444v32024arXiv

Earth+: on-board satellite imagery compression leveraging historical earth observations

Kuntai Du, Yihua Cheng, Peder Olsen et al.

9 citations

2403.11434v12024arXiv

Eloquent: A More Robust Transmission Scheme for LLM Token Streaming

Hanchen Li, Yuhan Liu, Yihua Cheng et al.

8 citations

2401.12961v22024arXiv

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

Yuhan Liu, Hanchen Li, Yihua Cheng et al.

117 citations

2310.07240v62023arXiv

Automatic and Efficient Customization of Neural Networks for ML Applications

Yuhan Liu, Chengcheng Wan, Kuntai Du et al.

0 citations

2310.04685v12023arXiv

OneAdapt: Fast Configuration Adaptation for Video Analytics Applications via Backpropagation

Kuntai Du, Yuhan Liu, Yitian Hao et al.

4 citations

2310.02422v22023arXiv

AccMPEG: Optimizing Video Encoding for Video Analytics

Kuntai Du, Qizheng Zhang, Anton Arapin et al.

11 citations

2204.12534v12022arXiv

Career total: 30 works. 18 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.