Dynamic Tensor Rematerialization

1 code implementation • ICLR 2021 • Marisa Kirisame, Steven Lyubomirsky, Altan Haan, Jennifer Brennan, Mike He, Jared Roesch, Tianqi Chen, Zachary Tatlock

Checkpointing enables the training of deep learning models under restricted memory budgets by freeing intermediate activations from memory and recomputing them on demand.

Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference

no code implementations • 4 Jun 2020 • Haichen Shen, Jared Roesch, Zhi Chen, Wei Chen, Yong Wu, Mu Li, Vin Sharma, Zachary Tatlock, Yida Wang

Modern deep neural networks increasingly make use of features such as dynamic control flow, data structures and dynamic tensor shapes.

Relay: A High-Level Compiler for Deep Learning

no code implementations • 17 Apr 2019 • Jared Roesch, Steven Lyubomirsky, Marisa Kirisame, Logan Weber, Josh Pollock, Luis Vega, Ziheng Jiang, Tianqi Chen, Thierry Moreau, Zachary Tatlock

Using these extension mechanisms, Relay supports a unified compiler that can target a variety of hardware platforms.

Relay: A New IR for Machine Learning Frameworks

no code implementations • 26 Sep 2018 • Jared Roesch, Steven Lyubomirsky, Logan Weber, Josh Pollock, Marisa Kirisame, Tianqi Chen, Zachary Tatlock

Machine learning powers diverse services in industry including search, translation, recommendation systems, and security.

BIG-bench Machine Learning Recommendation Systems +1