Yihua Cheng
Chief Technology Officer at Tensormesh
United States
Summary
🤩
Rockstar🎓
Top SchoolYihua Cheng is a technology leader and CTO with eight years of experience building real-time systems and ML infrastructure, currently leading engineering at TensorMesh. He has a strong research-to-product track record from internships at Conviva, Microsoft, Alibaba Cloud, and MEGVII, where he focused on real-time data processing, video conferencing platforms, TCP congestion control, and core ML engines. An active open-source core developer on projects like LMCache and vllm, he bridges high-performance model serving and production deployment. Yihua is pursuing a PhD in Computer Science at the University of Chicago after earning a CS bachelor’s from Peking University, combining rigorous academic training with hands-on systems engineering. Notably, his background emphasizes low-latency distributed systems and ML serving—skills he now applies to scale inference infrastructure at a startup pace.
8 years of coding experience
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at Peking UniversityDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Chicago
Github Skills (14)
xpu10
cuda10
llama10
transformer10
pytorch10
gpt10
mlops10
inference10
llmops10
tpu10
amd10
llm10
video-codec3
codec2
Programming languages (6)
Github contributions (5)
vllm-project/production-stack
Jan 2025 - Mar 2025
vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization
Contributions:87 reviews, 90 PRs, 82 pushes in 1 month
LMCache/LMCache
May 2024 - Mar 2025
Making Long-Context LLM Inference 10x Faster and 10x Cheaper
Contributions:5 releases, 141 reviews, 128 PRs in 9 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.