Contents
- 1. Overview
- 2. Overview
- 3. Introduction
- 4. Pre-installation Actions
- 5. Package Manager Installation
- 5.1. Overview
- 5.2. Red Hat Enterprise Linux / Rocky Linux / Oracle Linux
- 5.3. KylinOS
- 5.4. Fedora
- 5.5. SUSE Linux Enterprise Server
- 5.6. OpenSUSE Leap
- 5.7. Windows Subsystem for Linux
- 5.8. Ubuntu
- 5.9. Debian
- 5.10. Amazon Linux
- 5.11. Azure Linux
- 5.12. Additional Package Manager Capabilities
- 6. Driver Installation
- 7. Runfile Installation
- 8. Conda Installation
- 9. Pip Wheels
- 10. CUDA Cross-Platform Environment
- 11. Tarball and Zip Archive Deliverables
- 12. Post-installation Actions
- 13. Removing CUDA Toolkit
- 14. Advanced Setup
- 15. Additional Considerations
- 16. Frequently Asked Questions
- 16.1. How do I install the Toolkit in a different location?
- 16.2. Why do I see “nvcc: No such file or directory” when I try to build a CUDA application?
- 16.3. Why do I see “error while loading shared libraries: <lib name>: cannot open shared object file: No such file or directory” when I try to run a CUDA application that uses a CUDA library?
- 16.4. Why do I see multiple “404 Not Found” errors when updating my repository meta-data on Ubuntu?
- 16.5. How can I tell X to ignore a GPU for compute-only use?
- 16.6. Why doesn’t the cuda-repo package install the CUDA Toolkit?
- 16.7. How do I install an older CUDA version using a network repo?
- 16.8. How do I handle “Errors were encountered while processing: glx-diversions”?
- 17. Notices
- 18. Copyright