You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
TorchServe now supports model control mode with two settings "none"(default) and "enabled"
4
+
5
+
## Two ways to set Model Control
6
+
1. Add `--model-api-enabled` to command line when running TorchServe to switch from none to enabled mode. Command line cannot be used to set mode to none, can only be used to set to enabled
7
+
2. Add `model_api_enabled=false` or `model_api_enabled=true` to config.properties file
8
+
*`model_api_enabled=false` is default and prevents users from registering or deleting models once TorchServe is running
9
+
*`model_api_enabled=true` is not default and allows users to register and delete models using the TorchServe model load APIs
10
+
11
+
Priority between cmd and config file follows the following [TorchServer standard](https://github.com/pytorch/serve/blob/c74a29e8144bc12b84196775076b0e8cf3c5a6fc/docs/configuration.md#advanced-configuration)
Result: Mode is enabled (no way to disable api mode through cmd)
24
+
25
+
## Model Control Mode Default
26
+
At startup TorchServe loads only those models specified explicitly with the `--models` command-line option. After startup users will be unable to register or delete models in this mode.
0 commit comments