Deployment with a Custom Runtime

GPU functions can be deployed with a custom runtime.

For details about custom runtimes, see Custom Runtime.

These built-in runtimes are available: Python (Python 2.7.15), Python 3 (Python 3.6.8), Python 3.7 (Python 3.7.4), and Python 3.9 (Python 3.9.2).

Constraint: CUDA 11.6 is pre-integrated for function development. For other CUDA versions, use them with custom image–based functions.

For a function with a custom runtime, go to the function details page, choose Configuration > Basic Settings, and enable GPU.

Figure 1 Enabling GPU

Parent topic: Deployment Mode

Thank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.

The system is busy. Please try again later.

Which of the following issues have you encountered?

Content is inconsistent with the product UI

Unclear descriptions

Lack of examples or code

Incorrect steps

Can't find what I need

Lack of best practices

Feedback (optional)

0/500

Select at least one type of issue, and enter your comments or suggestions.

Enter a maximum of 500 characters.

Submit Cancel

For any further questions, feel free to contact us through the chatbot.