Contents
- 1. Introduction
- 2. Pre-installation Actions
-
3. Package Manager Installation
- 3.1. Overview
- 3.2. Red Hat Enterprise Linux / Rocky Linux / Oracle Linux
- 3.3. KylinOS
- 3.4. Fedora
- 3.5. SUSE Linux Enterprise Server
- 3.6. OpenSUSE Leap
- 3.7. Windows Subsystem for Linux
- 3.8. Ubuntu
- 3.9. Debian
- 3.10. Amazon Linux
- 3.11. Azure Linux
- 3.12. Additional Package Manager Capabilities
- 4. Driver Installation
- 5. Runfile Installation
- 6. Conda Installation
- 7. Pip Wheels
- 8. CUDA Cross-Platform Environment
- 9. Tarball and Zip Archive Deliverables
- 10. Post-installation Actions
- 11. Removing CUDA Toolkit
- 12. Advanced Setup
- 13. Additional Considerations
-
14. Frequently Asked Questions
- 14.1. How do I install the Toolkit in a different location?
- 14.2. Why do I see “nvcc: No such file or directory” when I try to build a CUDA application?
- 14.3. 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?
- 14.4. Why do I see multiple “404 Not Found” errors when updating my repository meta-data on Ubuntu?
- 14.5. How can I tell X to ignore a GPU for compute-only use?
- 14.6. Why doesn’t the cuda-repo package install the CUDA Toolkit?
- 14.7. How do I install an older CUDA version using a network repo?
- 14.8. How do I handle “Errors were encountered while processing: glx-diversions”?
- 15. Notices
- 16. Copyright