RAPIDS AI

Open source software for high performance, large-scale geospatial and spatiotemporal processing on GPUs

Using Regularized Regression on the regular? RAPIDS will let you train your models much faster on GPUs.

Accelerate GBDT and Random Forest Inference on GPUs.

If you know me, you know I love to reference songs, sports, movies, and TV shows as analogies. The RAPIDS 0.9 release brought to mind…

User-defined, custom kernels in Chainer CuPy

AKA Littlest CUDA Hub

Echoing the theme of our RAPIDS 0.8 release post, we want to encourage interoperability and enable an ecosystem. RAPIDS libraries and the…

By: Vibhu Jawa, Nick Becker, David Wendt and Randy Gelhausen

See Chainer’s CuPy performance for various data science operations running on a single GPU

Making more friends and building more bridges to more ecosystems. It’s now easier than ever to get started with RAPIDS.

A simple trading strategy backtest for 5000 stocks using GPUs and getting 20X speedup

See how RAPIDS was used to place 17th in the Banco Santander Kaggle Competition

RAPIDS XGBoost4J-Spark Package Now Available

A glimpse into how a Data Scientist makes decisions about featuring engineering an XGBoost machine learning model

Release code early and often. Stay current on latest features with our nightly conda and container releases.

Scale ETL workloads on GPUs with RAPIDS and Dask cuDF

Try out our early access Dask implementation on Google Cloud Dataproc, which is a service for launching clusters of VMs on GCP.

RAPIDS 0.7 is live! Like the Jeffersons, RAPIDS is improving in many ways. RAPIDS is available more places than ever before, and XGBoost…

Using the GPU for ETL and preprocessing of deep learning workflows

Like many projects, RAPIDS has struggled to find a solution that lets us integrate with the PyPI ecosystem without introducing all sorts of…

I recently had the privilege of presenting a workshop at the Curiosity Conference 2019. At this AI + Education conference, I demonstrated…

By: Rodrigo Aramburu

By Bianca Rhodes, Bhargav Suryadevara, and Nick Becker

There are a wide range of graph applications and algorithms that I hope to discuss through this series of blog posts, all with a bias…