#
moreh-switch-model
moreh-switch-model is a tool that allows you to change the flavor (specifications) of the currently configured MoAI Accelerator. By changing the flavor of the MoAI Accelerator, you determine how much GPU resource.
It can be used as follows:
For example, if the result of the moreh-smi command is as follows, it means that the "MoAI Platform AI Accelerator model currently set as the default is Accelerator 0, and this MoAI Accelerator is of type
Small.64GB
model."
+------------------------------------------------------------------------------------------------------+
| Current Version: 24.11.0 Latest Version: 24.11.0 |
+------------------------------------------------------------------------------------------------------+
| Device | Name | Model | Memory Usage | Total Memory | Utilization |
+======================================================================================================+
| * 0 | MoAI Accelerator | Small.64GB | - | - | - |
+------------------------------------------------------------------------------------------------------+The moreh-switch-model command displays the following prompt:
$ moreh-switch-model
Current MoAI Accelerator: Medium.128GB
1. Small.64GB *
2. Medium.128GB
3. Large.256GB
4. xLarge.512GB
5. 1.5xLarge.768GB
6. 2xLarge.1024GB
7. 3xLarge.1536GB
8. 4xLarge.2048GB
9. 6xLarge.3072GB
10. 8xLarge.4096GB
11. 12xLarge.6144GB
12. 24xLarge.12288GB
13. 48xLarge.24576GB
Selection (1-13, q, Q):
If you enter an integer corresponding to the model to be used from 1 to 13 (device number), the message "The MoAI Platform AI Accelerator model is successfully switched to {model_id}." will be displayed, and the MoAI Accelerator corresponding to the entered device number will be changed.
Let's change the MoAI Accelerator to Large.256GB as follows:
Selection (1-13, q, Q): 3
The MoAI Accelerator model is successfully switched to "Large.256GB".
1. Small.64GB
2. Medium.128GB
3. Large.256GB *
4. xLarge.512GB
5. 1.5xLarge.768GB
6. 2xLarge.1024GB
7. 3xLarge.1536GB
8. 4xLarge.2048GB
9. 6xLarge.3072GB
10. 8xLarge.4096GB
11. 12xLarge.6144GB
12. 24xLarge.12288GB
13. 48xLarge.24576GB
Selection (1-13, q, Q):
You can continue with the change or exit the MoAI Accelerator change by typing q or Q.
After the change is complete, when you run moreh-smi again to confirm, you will see the following result:
$ moreh-smi
+------------------------------------------------------------------------------------------------------+
| Current Version: 24.11.0 Latest Version: 24.11.0 |
+------------------------------------------------------------------------------------------------------+
| Device | Name | Model | Memory Usage | Total Memory | Utilization |
+======================================================================================================+
| * 0 | MoAI Accelerator | Large.256GB | - | - | - |
+------------------------------------------------------------------------------------------------------+The MoAI Accelerator previously set as the Small.64GB model has been changed to the Large.256GB model.