Yuhan Liu
I am a fifth-year Ph.D. student in the Department of Computer Science at the University of Chicago, advised by Prof. Junchen Jiang and Prof. Shan Lu. My research builds efficient inference systems for large language models — in particular, I've built the first compression and streaming system for KV cache that's designed to reduce its inline network transmission latency -- CacheGen, and the first translation system for KV cache between two different LLMs -- DroidSpeak.
I received my B.S. in Computer Science from the University of Wisconsin–Madison, where I was fortunate to be advised by Prof. Shivaram Venkataraman. In Summer 2024 I was a research intern at Microsoft Research, mentored by Madan Musuvathi and Esha Choukse.
Publications
* denotes equal contribution. Full list available on Google Scholar.
- DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving
- CacheBlend: Fast Large Language Model Serving with Cached Knowledge Fusion
- LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference
- CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving
- ChameleonAPI: Automatic and Efficient Customization of Neural Networks for ML Applications
- GRACE: Loss-Resilient Real-Time Video through Neural Codecs
- Keeper: Automated Testing and Fixing of Machine Learning Software
- OneAdapt: Fast Adaptation for Deep Learning Applications via Backpropagation
- Run-Time Prevention of Software Integration Failures of Machine Learning APIs
Open-Source Projects
LMCache
The first open-source Knowledge Delivery Network for LLM applications. Accelerates inference up to 8× at 8× lower cost.
vLLM Production Stack
Scale from a single vLLM instance to a distributed deployment without changing a line of application code.
Invited Talks & Awards
Invited Talks
- LLM Systems Seminar, Northeastern UniversityOct 2025
- Amazon RufusAug 2025
- Efficient AI Seminar, Rutgers UniversityMay 2025
- LLM Systems Class, Carnegie Mellon UniversityApr 2025
- Systems Group, University of MarylandMar 2025
- ML Systems Group, UC San DiegoMar 2025
- Systems Group, Duke UniversityNov 2024
- Distributed Systems Lab, U. PennsylvaniaNov 2024
Honors & Awards
- EECS Rising Star2025
- ACM EuroSys Best Paper Award2025
- UU Fellowship, UChicago2023
- Neubauer Graduate Scholarship, UChicago2021
- CRA Outstanding Undergraduate Researcher (Hon. Mention)2021
- Trewartha Honors Senior Thesis Award2020
Teaching & Service
Teaching
- TA · Graduate Networking (CMSC 33300)Autumn 2024
- TA · Intro to Computer Systems (CMSC 15400)Winter 2022
- Peer Mentor · Intro to DB Systems (CS 564, UW-Madison)Fall 2020
Mentoring
- Hanchen Li → PhD, UC Berkeley2023 – 2025
- Zhuohan Gu → PhD, MIT2024 – 2025
- Shaoting Feng → PhD, University of Washington2024 –
Service
- Organizer · SIGCOMM '25 Tutorial: Networking for Stateful LLM Inference2025
- Co-Chair · Graduate Women in CS, UChicago2024 – 2025
- Reviewer · NeurIPS, ICML2022
- Reviewer · ICML2025
Industry
- Research Intern, Microsoft ResearchSummer 2024