Yiming Cheng is a Pre-doc researcher in the Department of Computer Science at the University of Chicago, where he is pursuing an M.S. in Computer Science with a specialization in Machine Learning Systems (MLSys track). He graduated from Tsinghua University in 2024 with a Bachelor of Engineering in Electronic Engineering, along with minors in Statistics and Law.

Currently, Yiming is working as an Open Source Contributor and Research Assistant with the LMCache team under the supervision of Prof. Junchen Jiang. His work focuses on LMCache, the first open-source Knowledge Delivery Network (KDN) that accelerates LLM applications up to 8x faster at 8x lower cost. He also contributes to vLLM/production-stack, helping scale from single vLLM instances to distributed vLLM deployments. He has contributed over 1,262 lines of code to these open-source projects.

His research interests span both systems for machine learning (distributed LLM deployment, distributed KV cache, efficient ML) and machine learning for systems (ML for code generation and Operating Systems). During his undergraduate studies, he worked extensively on data mining projects including recommendation systems, emotion awareness, and embodied city simulations.

Yiming has been recognized with several prestigious awards, including the Merit-based Predoc Scholarship of $40,000 from the University of Chicago and funding from the United States National Science Foundation for his Summer of Reproducibility (SoR) project. He has authored multiple publications in venues such as MDPI Sensors and has patents in semantic encoding and decoding frameworks.

Through his research at institutions including Argonne National Laboratory, Tsinghua University’s Future Intelligent Lab, and the University of Houston, Yiming continues to contribute to advancing distributed computing technologies and machine learning systems. His expertise in programming languages including Python (PyTorch, CuPy), Go (Docker, K8s), and various other technologies makes him a valuable contributor to the open-source machine learning community.