Tianqi Chen
Started MLC LLM, a compiler-based engine for running language models on GPUs, phones, and browsers
- Associate Professor, Machine Learning Department and Computer Science Department, Carnegie Mellon University1
- Distinguished Engineer, NVIDIA1
Tianqi Chen is an Associate Professor in the Machine Learning and Computer Science departments at Carnegie Mellon University and a Distinguished Engineer at NVIDIA. Chen lists MLC LLM among the machine learning systems Chen started. MLC LLM uses machine learning compilation to deploy language models natively on AMD, NVIDIA, Apple, and Intel GPUs, in web browsers, and on iOS and Android devices. Chen's earlier projects include Apache TVM, an open machine learning compilation framework.123
Work
MLC LLM
Listed by Chen among the machine learning systems Chen started. The Apache-2.0 repository, which credits the MLC team as authors, describes a universal deployment engine for language models built on machine learning compilation.12
Apache TVM (external site: github.com)
Listed by Chen among the systems Chen started. The Apache-2.0 project is an open machine learning compilation framework that began as a research project on deep learning compilation.13
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.