The Lambda
Deep Learning Blog

Published on June 3, 2020 by Chuan Li

by Chuan Li, PhD

Published on May 22, 2020 by Stephen Balaban

Lambda customers are starting to ask about the new NVIDIA A100 GPU and our Hyperplane A100 server. The A100 will likely see the large gains on models like ...

Published on May 13, 2020 by Remy Guercio

With most (if not all) machine learning and deep learning researchers and engineers now working from home due to COVID-19, we’ve seen a massive increase in the ...

Published on May 3, 2020 by Remy Guercio

You can now use Lambda Cloud High Speed Filesystems to permanently store data on the Lambda Cloud. Click here to learn how to use Lambda Cloud Filesystems.

Published on May 3, 2020 by Remy Guercio

This guide will walk you through the process of launching a Lambda Cloud GPU instance and using SSH to log in. While we offer both a Web Terminal and Jupyter ...

Published on April 7, 2020 by Stephen Balaban

In this post we'll walk through using our Total Cost of Ownership (TCO) calculator to examine the cost of a variety of Lambda Hyperplane-16 clusters. We have ...

Published on February 18, 2020 by Michael Balaban

State-of-the-art (SOTA) deep learning models have massive memory footprints. Many GPUs don't have enough VRAM to train them. In this post, we determine which ...

Published on December 19, 2019 by Chuan Li

by Chuan Li, PhD

Published on October 30, 2019 by Stephen Balaban

The desired end-state of this tutorial, a running subnet manager on your switch. This tutorial will walk you through the steps required to set up a Mellanox ...

Published on October 1, 2019 by Chuan Li

TensorFlow 2 is now live! This tutorial walks you through the process of building a simple CIFAR-10 image classifier using deep learning. In this tutorial, we ...

Published on August 28, 2019 by Chuan Li

This blog will walk you through the steps of setting up a Horovod + Keras environment for multi-GPU training.

Published on August 12, 2019 by Chuan Li

One of the most asked questions we get at Lambda Labs is, “how do I track resource utilization for deep learning jobs?” Resource utilization tracking can help ...

Published on June 7, 2019 by Chuan Li

Distributed training allows scaling up deep learning task so bigger models can be learned or training can be conducted at a faster pace. In a previous ...

Published on June 6, 2019 by Chuan Li

During training, weights in the neural networks are updated so that the model performs better on the training data. For a while, improvements on the training ...

Published on June 6, 2019 by Chuan Li

This tutorial combines two items from previous tutorials: saving models and callbacks. Checkpoints are saved model states that occur during training. With ...