检测到您已登录华为云国际站账号，为了您更好的体验，建议您访问国际站服务网站 https://www.huaweicloud.com/intl/zh-cn
不再显示此消息
检测到您已登录华为云国际站账号，为了您更好的体验，建议您访问国际站服务网站 https://www.huaweicloud.com/intl/zh-cn
不再显示此消息
A model is deployed as a web service on an edge node through Intelligent EdgeFabric (IEF). that provides a real-time test UI and monitoring capabilities. The service keeps running. You need to create a node on IEF beforehand.]
The notebook instances with remote SSH enabled have VS Code plug-ins (such as Python and Jupyter) and the VS Code server package pre-installed, which occupy about 1 GB persistent storage space. Key Pair Set a key pair after remote SSH is enabled.
You can set CPU (vCPUs), Memory (GB), Ascend (PU), and Compute Nodes as required. Custom specifications must match or stay below the node specifications of the dedicated resource pool. For CPU specifications, you can only customize the number of vCPUs and memory.
MindSpeed-LLM Throughput (tokens/s/p): Global batch size x sequence length/(Total number of PUs x elapsed time per iteration) x 1000. The global batch size (GBS) and sequence length (SEQ_LEN) are set during training and printed in the logs.
Letters, digits, and hyphens (-) are allowed.
Letters, digits, and hyphens (-) are allowed.
Adjust the values of micro-batch-size (MBS, minimum number of samples processed in a batch) and global-batch-size (GBS, number of samples processed in an iteration).
The maximum size of the content to be injected (before encoding) is 32K. Range: N/A Default Value: N/A Response Parameters Status code: 200 Table 3 Response header parameters Parameter Type Description X-Request-Id String Link trace ID.
The maximum size of the content to be injected (before encoding) is 32K. Range: N/A Default Value: N/A Response Parameters Status code: 200 Table 3 Response header parameters Parameter Type Description X-Request-Id String Link trace ID.
Lowercase letters, digits, hyphens (-), underscores (_), and periods (.) are allowed. namespace String Definition: Organization to which the image belongs. You can create and view an organization on the Organization Management page of the SWR console.
It is recommended that the Linux server have sufficient memory (more than 8 GB) and hard disk (more than 100 GB).
If the model service (server) initiates a disconnection, but the connection is being used by ModelArts (client), a communication error occurs and this error code is returned.
The maximum size of the content to be injected (before encoding) is 32K. Range: N/A Default Value: N/A Response Parameters Status code: 200 Table 3 Response header parameters Parameter Type Description X-Request-Id String Link trace ID.
Node Pool Flavor Node Type Common node: A physical or virtual server that provides independent basic compute, storage, and network resources.
Creating a ModelArts Agency This API is used to create a ModelArts agency for ModelArts-dependent services, such as Object Storage Service (OBS), Software Repository for Container (SWR), and Intelligent EdgeFabric (IEF).
Parameter Settings Collection Period (s) If the cluster scale is large (≥ 200 nodes or ≥ 10,000 Pods), set this parameter to 60 or 30. Data Retention Period Set the data retention period.
Node Type Common node: A physical or virtual server that provides independent basic compute, storage, and network resources.
It is recommended that the Linux server have sufficient memory (more than 8 GB) and hard disk (more than 100 GB).
Number ≥ 0 N/A N/A N/A Node Compute PU Allocation Rate Total number of compute PUs on a node ma_node_total_card Number of compute (GPU or NPU) PUs on a node Number ≥ 0 N/A N/A N/A Number of allocated compute PUs on a node ma_node_allocate_card Number of compute (GPU or NPU) PUs on
Table 4 Elastic node server Application Scenario Dependent Service Dependent Policy Supported Function Elastic node server lifecycle management ModelArts modelarts:devserver:create modelarts:devserver:listByUser modelarts:devserver:list modelarts:devserver:get modelarts:devserver:
