Compiler

PyTorch 2: Faster Machine Learning Through Dynamic Python Bytecode Transformation and Graph Compilation

This paper introduces two extensions to the popular PyTorch machine learning framework, TorchDynamo and TorchInductor, which implement …

Jason Ansel, Edward Yang, Horace He, Natalia Gimelshein, Animesh Jain, Michael Voznesensky, Bin Bao, Peter Bell, David Berard, Evgeni Burovski, Geeta Chauhan, Anjali Chourdia, Will Constable, Alban Desmaison, Zachary DeVito, Elias Ellison, Will Feng, Jiong Gong, Michael Gschwind, Brian Hirsh, Sherlock Huang, Kshiteej Kalambarkar, Laurent Kirsch, Michael Lazos, Mario Lezcano, Yanbo Liang, Jason Liang, Yinghai Lu, C. K. Luk, Bert Maher, Yunjie Pan, Christian Puhrsch, Matthias Reso, Mark Saroufim, Marcos Yukio Siraichi, Helen Suk, Shunting Zhang, Michael Suo, Phil Tillet, Xu Zhao, Eikan Wang, Keren Zhou, Richard Zou, Xiaodong Wang, Ajit Mathews, William Wen, Gregory Chanan, Peng Wu, Soumith Chintala

Technical Review on PyTorch 2.0 and Triton

High-level overview of PyTorch 2.0 and Triton integration

Aug 7, 2023 10:03 PM — 10:03 PM Virtual

Triton is a language and compiler for writing highly efficient custom Deep-Learning primitives. The aim of Triton is to provide an open-source environment for expressing tensor math workloads that offers high flexibility, developer productivity and end to end performance.

Triton

Towards Agile Development of Efficient Deep Learning Operators (Pre-MLIR)

Presented triton programming language and its next step

Dec 2, 2022 10:03 PM — 10:03 PM Virtual

Practical Performance Optimization for Deep Learning Applications

Presented triton programming language and a deep learning profiler

May 18, 2022 10:02 PM — 10:02 PM Virtual