MLSys: Guest Talk

  • Remote Access - Zoom
  • Virtual Presentation - ET
Talks

Hummingbird: A Tensor Compiler for Unified Machine Learning Prediction Serving

Machine Learning (ML) adoption in the enterprise requires simpler and more efficient software infrastructure. Model scoring, the process of obtaining prediction from a trained model over new data, is a primary contributor to infrastructure complexity and cost, as models are trained once but used many times.

Hummingbird is a novel approach to model scoring, which compiles featurization operators and traditional ML models (e.g., decision trees) into a small set of tensor operations. This approach inherently reduces infrastructure complexity and directly leverages existing investments in Neural Networks’ compilers and runtimes to generate efficient computations for both CPU and hardware accelerators. Hummingbird performance are competitive and even outperforms hand-crafted kernels while enabling seamless end-to-end acceleration of ML pipelines. Hummingbird is open source, part of the PyTorch Ecosystem, and someone even mentioned it as one of the top 10 Python libraries of 2020! In this talk we will go over the past, present, and future of Hummingbird.

Speakers

►  Matteo Interlandi is a Senior Scientist in the Gray Systems Lab (GSL) at Microsoft, working on scalable Machine Learning systems. Before Microsoft, he was a Postdoctoral Scholar in the CS Department at the University of California, Los Angeles, working on Big Data systems. Prior to joining UCLA, he was a researcher at the Qatar Computing Research Institute, and at the Institute for Human and Machine Cognition. He obtained his PhD in Computer Science from the University of Modena and Reggio Emilia.

►  Karla Saur is a Senior Research Software Development Engineer in the Gray Systems Lab (GSL) at Microsoft. She finished her PhD in Computer Science at the University of Maryland, College Park in 2015. After graduating, Karla spent 3 years as a research scientist at Intel Labs and joined Microsoft in 2018. Her research interests are broad, and generally enjoys scalability and performance challenges related to systems infrastructure.

Faculty Host: Tianqi Chen

Zoom Participation. See announcement.

For More Information, Please Contact: 
Keywords: