Why Cannot I Select Ascend 310 Resources?
Ascend 310 resources are limited. If resources are sold out, you cannot select Ascend 310 resources (in the public resource pool) for inference during deployment. On the Deploy page, the Ascend: 1*Ascend-D310(8 GB) | ARM: 3 vCPUs, 6 GB resource will be unavailable.
Solutions:
- Method 1: If you want to use Ascend 310 in the public resource pool, you can wait for other users to release the resources. If other services using the Ascend 310 resources stop, you can select the resources for deployment.
- Method 2: If you have a dedicated resource pool with Ascend 310 resources, you can create an Ascend 310 dedicated resource pool.
- Method 3: If Ascend 310 resources in the dedicated resource pool are sold out, you can create an Ascend 310 dedicated resource pool after other users have deleted their Ascend 310 instances.
Functional Consulting FAQs
- What Types of Services Can Models Be Deployed as on ModelArts?
- What Are the Differences Between Real-Time Services and Batch Services?
- Why Cannot I Select Ascend 310 Resources?
- Can Models Trained on ModelArts Be Deployed Locally?
- What Is the Maximum Size of a Prediction Request Body?
- Can Real-Time Services Be Billed on a Yearly/Monthly Basis?
- How Do I Select Compute Node Specifications for Deploying a Service?
- What Is the CUDA Version for Deploying a Service on GPUs?
Feedback
Was this page helpful?
Provide feedbackThank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.
For any further questions, feel free to contact us through the chatbot.
Chatbotmore