OpenSeq2Seq: New Toolkit for Distributed and Mixed-Precision Training of Sequence-to-Sequence Models

Artificial Intelligence, Machine Learning & Artificial Intelligence, Volta

Nadeem Mohammad, posted Apr 21 2018

Researchers at NVIDIA open-sourced v0.2 of OpenSeq2Seq – a new toolkit built on top of TensorFlow for training sequence-to-sequence models.

Read more

Using CUDA Warp-Level Primitives

Accelerated Computing, Cooperative Groups, CUDA, Development Tools and Libraries, Volta

Nadeem Mohammad, posted Jan 15 2018

NVIDIA GPUs execute groups of threads known as warps in SIMT (Single Instruction, Multiple Thread) fashion. Many CUDA programs achieve high performance by taking advantage of warp execution.

Read more

Microsoft Releases New Version of High-Performance, Open-Source, Deep Learning Toolkit

News, Research, Higher Education / Academia, Image Recognition, Machine Learning & Artificial Intelligence, Volta

Nadeem Mohammad, posted Jun 01 2017

Previously known as CNTK, the Microsoft Cognitive Toolkit version 2.0 allows developers to create, train, and evaluate their own neural networks that can scale across multiple GPUs and multiple machines on massive data sets.

Read more