Add additional ML cluster settings ()

* Add experimental ML settings

Signed-off-by: Naarcha-AWS <naarcha@amazon.com>

* Apply suggestions from code review

Add tech review feedback

Co-authored-by: Yaliang Wu <ylwu@amazon.com>
Signed-off-by: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>

---------

Signed-off-by: Naarcha-AWS <naarcha@amazon.com>
Signed-off-by: Naarcha-AWS <97990722+Naarcha-AWS@users.noreply.github.com>
Co-authored-by: Yaliang Wu <ylwu@amazon.com>
This commit is contained in:
Naarcha-AWS 2023-06-23 11:47:22 -05:00 committed by GitHub
parent f42bda00a6
commit 3527245634
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 57 additions and 7 deletions
_ml-commons-plugin

View File

@ -103,14 +103,14 @@ plugins.ml_commons.monitoring_request_count: 100
- Default value: `100`
- Value range: [0, 10,000,000]
## Upload model tasks per node
## Register model tasks per node
Controls how many upload model tasks can run in parallel on one node. If set to `0`, you cannot upload models to any node.
Controls how many register model tasks can run in parallel on one node. If set to `0`, you cannot run register model tasks on any node.
### Setting
```
plugins.ml_commons.max_upload_model_tasks_per_node: 10
plugins.ml_commons.max_register_model_tasks_per_node: 10
```
@ -120,14 +120,14 @@ plugins.ml_commons.max_upload_model_tasks_per_node: 10
- Value range: [0, 10]
## Load model tasks per node
## Deploy model tasks per node
Controls how many load model tasks can run in parallel on one node. If set to 0, you cannot load models to any node.
Controls how many deploy model tasks can run in parallel on one node. If set to 0, you cannot deploy models to any node.
### Setting
```
plugins.ml_commons.max_load_model_tasks_per_node: 10
plugins.ml_commons.max_deploy_model_tasks_per_node: 10
```
### Values
@ -135,9 +135,39 @@ plugins.ml_commons.max_load_model_tasks_per_node: 10
- Default value: `10`
- Value range: [0, 10]
## Register models using URLs
This setting gives you the ability to register models using a URL. By default, ML Commons only allows registration of [pretrained]({{site.url}}{{site.baseurl}}//ml-commons-plugin/pretrained-models/) models from the OpenSearch model repository.
### Setting
```
plugins.ml_commons.allow_registering_model_via_url: false
```
### Values
- Default value: false
- Value range: [false, true]
## Register models using local files
This setting gives you the ability to register a model using a local file. By default, ML Commons only allows registration of [pretrained]({{site.url}}{{site.baseurl}}//ml-commons-plugin/pretrained-models/) models from the OpenSearch model repository.
### Setting
```
plugins.ml_commons.allow_registering_model_via_local_file: false
```
### Values
- Default value: false
- Value range: [false, true]
## Add trusted URL
The default value allows you to upload a model file from any http/https/ftp/local file. You can change this value to restrict trusted model URLs.
The default value allows you to register a model file from any http/https/ftp/local file. You can change this value to restrict trusted model URLs.
### Setting
@ -246,3 +276,23 @@ plugins.ml_commons.model_auto_redeploy_success_ratio: 0.8
- Default value: 0.8
- Value range: [0, 1]
## Run Python-based models
When set to `true`, this setting enables the ability to run Python-based models supported by OpenSearch, such as [Metrics correlation]({{site.url}}{{site.baseurl}}/ml-commons-plugin/algorithms/#metrics-correlation).
### Setting
```
plugins.ml_commons.enable_inhouse_python_model: false
```
### Values
- Default value: false
- Value range: [false, true]