🎮
About Me
Juntao Zhao is a PhD Candidate at the University of Hong Kong. His research focuses on machine learning systems (Mlsys), with a specific emphasis on efficient inference and training of large foundation models (LFM), including vision-language models (VLM) and large language models (LLM), as well as quantization techniques. He also has a solid background in games and blockchain.
Interests
- Machine Learning System
- Games
- Blockchain
Education
-
PhD in Machine Learning System
University of Hong Kong
-
BSc Computer Science And Technology
The Chinese University of Hong Kong (shenzhen)
👔 Open for Job
I am graduating late 2025. Consider my background, I am seeking full-time roles in LLM inference optimization (kernel development, custom chip design, quantization, distributed inference). Also interested in game development and blockchain (hands-on project experience in V/AR and game projects, papers on blockchain)..
Please reach out to if you are hiring 😃
Recent Publications
(2025).
Efficient LLM Serving on Hybrid Real-time and Best-effort Requests.
arXiv preprint arXiv:2504.09590.
(2025).
OVERLORD: Ultimate Scaling of DataLoader for Multi-Source Large Foundation Model Training.
arXiv preprint arXiv:2504.09844.
(2024).
Cdmpp: A device-model agnostic framework for latency prediction of tensor programs.
Proceedings of the Nineteenth European Conference on Computer Systems.
(2024).
Llm-pq: Serving llm on heterogeneous clusters with phase-aware partition and adaptive quantization.
arXiv preprint arXiv:2403.01136.
(2024).
POSTER: LLM-PQ: Serving LLM on Heterogeneous Clusters with Phase-Aware Partition and Adaptive Quantization.
Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming.