Skip to main content

Python interface to CUDA Multi-Process Service

Project description

Package Description

CUDAMPS is a Python interface to the CUDA Multi-Process Service. It supports creation and management of MPS control daemons for multiple GPUs.

Latest Version Downloads

Prerequisites

  • At least one Tesla or Quadro GPU with compute capability 3.5 or later.

  • CUDA 7.0 or later.

  • PyCUDA.

  • Pytools.

When used with Python 2.7, subprocess32 is also required.

Installation

The package may be installed as follows:

pip install cudamps

Usage

See the file demo.py for an example of how to use the package.

Development

The latest release of the package may be obtained from GitHub.

Author

See the included AUTHORS.rst file for more information.

License

This software is licensed under the BSD License. See the included LICENSE.rst file for more information.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cudamps-0.1.1.tar.gz (8.9 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page