Deepstream installation for a system with Nvidia GPU

[edit_or]

I have two questions.
Can I install Deepstream to a system with Nvidia GPU, but not Nvidia’s edge devices (Xavier, Nano, TX1, TX2)?

I have an application using Xavier.
Users there just turn off the device using switch. They don’t care shutting down OS first to turn off.
So how can I manage when they switch off, internal application shutdown the OS by itself. Is it possible?

[kesong]

Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

---

[edit_or]

Pls look at my questions. Nothing related to a specific device.

[kayccc]

@edit_or

Can I install Deepstream to a system with Nvidia GPU, but not Nvidia’s edge devices (Xavier, Nano, TX1, TX2)?

Yes, the DeepStream SDK release can support Tesla T4, and Ampere GPUs.
Please refer to DeepStream Getting Started | NVIDIA Developer

[edit_or]

Thanks so I can use Deepstream for a server with A30 GPUs.
Can pls share installation process for server?
We use sdkmanager for edge devices.
For server, any installation instructions?

[kayccc]

Please refer to NVIDIA DeepStream SDK Developer Guide — DeepStream 6.0.1 Release documentation