Pipeline Parallelism for DNN Inference with Practical Performance Guarantees

no code implementations • 7 Nov 2023 • Aaron Archer, Matthew Fahrbach, Kuikui Liu, Prakash Prabhu

We optimize pipeline parallelism for deep neural network (DNN) inference by partitioning model graphs into $k$ stages and minimizing the running time of the bottleneck stage, including communication.

A Transferable Approach for Partitioning Machine Learning Models on Multi-Chip-Modules

no code implementations • 7 Dec 2021 • Xinfeng Xie, Prakash Prabhu, Ulysse Beaugnon, Phitchaya Mangpo Phothilimthana, Sudip Roy, Azalia Mirhoseini, Eugene Brevdo, James Laudon, Yanqi Zhou

Partitioning ML graphs for MCMs is particularly hard as the search space grows exponentially with the number of chiplets available and the number of nodes in the neural network.

BIG-bench Machine Learning Reinforcement Learning (RL) +1