Google Inc.

Ryan Sepassi

Noam M Shazeer

Lukasz Mieczyslaw Kaiser

Peter Junteng Liu

Ben David Goodrich

Mohammad Saleh

Etienne Pot

Jeffrey Adgate Dean

Sanjay Ghemawat

Yonghui Wu

Ruoming Pang

Michael Isard

Chandramohan Amyangot Thekkath

Paul Ronald Barham

Sudip Roy

Aakanksha Chowdhery

Laurent El Shafey

Brennan Saeta

Daniel William Hurt

Hyeontaek Lim

Parker Edward Schuh

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. One of the methods includes, at each of a plurality of generation time steps: generating a combined sequence for the generation time step that includes the input sequence followed by the output tokens that have already been generated as of the generation time step; processing the combined sequence using a self-attention decoder neural network to generate a time step output that defines a score distribution over a set of possible output tokens; and selecting, using the time step output, an output token from the set of possible output tokens as the next output token in the output sequence.

Attention-based decoder-only sequence transduction neural networks

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for distributing machine learning workloads, e.g., computations for training a neural network or computing an inference using a neural network, across multiple hardware accelerators. One of the systems comprises a plurality of accelerator islands, each hardware accelerator island comprising a respective plurality of hardware devices that include a plurality of hardware accelerators and a corresponding host for each of the plurality of hardware accelerators; and a respective scheduler for each of the accelerator islands that is configured to schedule workloads across the plurality of accelerators and corresponding hosts in the accelerator island, wherein the system is configured to: receive data representing a machine learning workload; and assign a respective portion of the machine learning workload to each of the plurality of accelerator islands for scheduling by the respective scheduler for the accelerator island.

Asynchronous distributed data flow for machine learning workloads

Growing community of inventors

Palo Alto, CA, United States of America

Ryan Sepassi