Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ No description provided (generated by Openapi Generator https://github.com/opena
This Python package is automatically generated by the [OpenAPI Generator](https://openapi-generator.tech) project:

- API version: 0.1.0
- Package version: 4.28.0
- Package version: 4.29.0
- Generator version: 7.9.0
- Build package: org.openapitools.codegen.languages.PythonClientCodegen

Expand Down Expand Up @@ -108,7 +108,6 @@ Class | Method | HTTP request | Description
*EXTERNALApi* | [**create_volume_endpoint_volumes_post**](docs/EXTERNALApi.md#create_volume_endpoint_volumes_post) | **POST** /volumes | Create Volume Endpoint
*EXTERNALApi* | [**delete_cluster_clusters_cluster_id_delete**](docs/EXTERNALApi.md#delete_cluster_clusters_cluster_id_delete) | **DELETE** /clusters/{cluster_id} | Delete Cluster
*EXTERNALApi* | [**delete_hardware_instance_hardware_instances_hardware_instance_id_delete**](docs/EXTERNALApi.md#delete_hardware_instance_hardware_instances_hardware_instance_id_delete) | **DELETE** /hardware-instances/{hardware_instance_id} | Delete Hardware Instance
*EXTERNALApi* | [**delete_org_gpu_quota_on_cluster_clusters_cluster_id_organizations_organization_id_gpu_quota_delete**](docs/EXTERNALApi.md#delete_org_gpu_quota_on_cluster_clusters_cluster_id_organizations_organization_id_gpu_quota_delete) | **DELETE** /clusters/{cluster_id}/organizations/{organization_id}/gpu-quota | Delete Org Gpu Quota On Cluster
*EXTERNALApi* | [**delete_service_account_service_accounts_workos_id_delete**](docs/EXTERNALApi.md#delete_service_account_service_accounts_workos_id_delete) | **DELETE** /service-accounts/{workos_id} | Delete Service Account
*EXTERNALApi* | [**delete_user_vault_item_by_id_endpoint_user_vault_secret_id_delete**](docs/EXTERNALApi.md#delete_user_vault_item_by_id_endpoint_user_vault_secret_id_delete) | **DELETE** /user_vault/{secret_id} | Delete User Vault Item By Id Endpoint
*EXTERNALApi* | [**delete_user_vault_item_endpoint_user_vault_delete**](docs/EXTERNALApi.md#delete_user_vault_item_endpoint_user_vault_delete) | **DELETE** /user_vault | Delete User Vault Item Endpoint
Expand Down
7 changes: 4 additions & 3 deletions docs/CreateDynamoDeploymentRequest.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# CreateDynamoDeploymentRequest

Create a Dynamo deployment. Aggregated mode requires ``hardware_instance_id``; disaggregated mode requires fixed-size ``worker_pools``.
Create a Dynamo deployment. Hardware and scaling live under ``worker_pools``: aggregated mode uses exactly ``worker_pools.worker``; disaggregated mode uses exactly ``worker_pools.prefill`` and ``worker_pools.decode`` (fixed-size until per-role autoscaling ships). The top-level ``hardware_instance_id`` / ``min_replicas`` / ``max_replicas`` / ``concurrency`` / ``cooldown_period`` fields are the deprecated aggregated-only spelling; they stay accepted and may accompany ``worker_pools`` when they agree with it. ``parse_dynamo_topology`` owns every topology rule for both spellings.

## Properties

Expand All @@ -17,8 +17,9 @@ Name | Type | Description | Notes
**worker_pools** | [**DynamoWorkerPools**](DynamoWorkerPools.md) | | [optional]
**model** | **str** | |
**served_model_name** | **str** | | [optional]
**min_replicas** | **int** | | [optional] [default to 1]
**max_replicas** | **int** | | [optional] [default to 1]
**runtime_version** | **str** | Dynamo runtime image tag (for example 1.4.0). Defaults to the platform's current release; GET /prebuilt-images?type=dynamo lists the versions the platform has validated, but any tag may be requested. Changing it restarts every component of a running deployment. | [optional]
**min_replicas** | **int** | | [optional]
**max_replicas** | **int** | | [optional]
**concurrency** | **int** | | [optional]
**cooldown_period** | **int** | | [optional]
**extra_args** | **str** | | [optional]
Expand Down
6 changes: 6 additions & 0 deletions docs/DeploymentResponse.md
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,7 @@ Name | Type | Description | Notes
**worker_pools** | [**DynamoWorkerPools**](DynamoWorkerPools.md) | | [optional]
**model** | **str** | |
**served_model_name** | **str** | | [optional]
**runtime_version** | **str** | | [optional]
**min_replicas** | **int** | |
**max_replicas** | **int** | |
**concurrency** | **int** | | [optional]
Expand All @@ -47,6 +48,11 @@ Name | Type | Description | Notes
**volume_mounts** | [**List[VolumeMount]**](VolumeMount.md) | | [optional]
**ssh_public_key** | **str** | | [optional]
**ssh_password** | **str** | | [optional]
**args** | **List[str]** | | [optional]
**completions** | **int** | | [optional] [default to 1]
**parallelism** | **int** | | [optional] [default to 1]
**backoff_limit** | **int** | | [optional] [default to 3]
**active_deadline_seconds** | **int** | | [optional]

## Example

Expand Down
7 changes: 6 additions & 1 deletion docs/DynamoWorkerPoolConfig.md
Original file line number Diff line number Diff line change
@@ -1,12 +1,17 @@
# DynamoWorkerPoolConfig

Hardware and scaling for one Dynamo worker role. ``min_replicas``/``max_replicas`` are the canonical size. ``replicas`` is the deprecated fixed-size alias (``min == max``) still accepted on disaggregated pools. ``parse_dynamo_topology`` owns the cross-field rules (bounds ordering, autoscaling target, which roles may autoscale).

## Properties

Name | Type | Description | Notes
------------ | ------------- | ------------- | -------------
**hardware_instance_id** | **int** | |
**replicas** | **int** | |
**replicas** | **int** | | [optional]
**min_replicas** | **int** | | [optional]
**max_replicas** | **int** | | [optional]
**concurrency** | **int** | | [optional]
**cooldown_period** | **int** | | [optional]

## Example

Expand Down
5 changes: 3 additions & 2 deletions docs/DynamoWorkerPools.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,9 @@

Name | Type | Description | Notes
------------ | ------------- | ------------- | -------------
**prefill** | [**DynamoWorkerPoolConfig**](DynamoWorkerPoolConfig.md) | |
**decode** | [**DynamoWorkerPoolConfig**](DynamoWorkerPoolConfig.md) | |
**worker** | [**DynamoWorkerPoolConfig**](DynamoWorkerPoolConfig.md) | | [optional]
**prefill** | [**DynamoWorkerPoolConfig**](DynamoWorkerPoolConfig.md) | | [optional]
**decode** | [**DynamoWorkerPoolConfig**](DynamoWorkerPoolConfig.md) | | [optional]

## Example

Expand Down
90 changes: 6 additions & 84 deletions docs/EXTERNALApi.md
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,6 @@ Method | HTTP request | Description
[**create_volume_endpoint_volumes_post**](EXTERNALApi.md#create_volume_endpoint_volumes_post) | **POST** /volumes | Create Volume Endpoint
[**delete_cluster_clusters_cluster_id_delete**](EXTERNALApi.md#delete_cluster_clusters_cluster_id_delete) | **DELETE** /clusters/{cluster_id} | Delete Cluster
[**delete_hardware_instance_hardware_instances_hardware_instance_id_delete**](EXTERNALApi.md#delete_hardware_instance_hardware_instances_hardware_instance_id_delete) | **DELETE** /hardware-instances/{hardware_instance_id} | Delete Hardware Instance
[**delete_org_gpu_quota_on_cluster_clusters_cluster_id_organizations_organization_id_gpu_quota_delete**](EXTERNALApi.md#delete_org_gpu_quota_on_cluster_clusters_cluster_id_organizations_organization_id_gpu_quota_delete) | **DELETE** /clusters/{cluster_id}/organizations/{organization_id}/gpu-quota | Delete Org Gpu Quota On Cluster
[**delete_service_account_service_accounts_workos_id_delete**](EXTERNALApi.md#delete_service_account_service_accounts_workos_id_delete) | **DELETE** /service-accounts/{workos_id} | Delete Service Account
[**delete_user_vault_item_by_id_endpoint_user_vault_secret_id_delete**](EXTERNALApi.md#delete_user_vault_item_by_id_endpoint_user_vault_secret_id_delete) | **DELETE** /user_vault/{secret_id} | Delete User Vault Item By Id Endpoint
[**delete_user_vault_item_endpoint_user_vault_delete**](EXTERNALApi.md#delete_user_vault_item_endpoint_user_vault_delete) | **DELETE** /user_vault | Delete User Vault Item Endpoint
Expand Down Expand Up @@ -81,6 +80,8 @@ Method | HTTP request | Description

Create Cluster

Register a cluster row for the caller's parent org. Infra provisioning is not wired yet; ``request.credential`` is validated but not consumed.

### Example

* Bearer Authentication (HTTPBearer):
Expand Down Expand Up @@ -1132,87 +1133,6 @@ void (empty response body)

[[Back to top]](#) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to Model list]](../README.md#documentation-for-models) [[Back to README]](../README.md)

# **delete_org_gpu_quota_on_cluster_clusters_cluster_id_organizations_organization_id_gpu_quota_delete**
> OrganizationGpuQuotaResponse delete_org_gpu_quota_on_cluster_clusters_cluster_id_organizations_organization_id_gpu_quota_delete(cluster_id, organization_id)

Delete Org Gpu Quota On Cluster

Set persisted quota to unlimited (-1). Creates a row if none exists. Does not remove the row or the KAI Queue CR.

### Example

* Bearer Authentication (HTTPBearer):

```python
import platform_api_python_client
from platform_api_python_client.models.organization_gpu_quota_response import OrganizationGpuQuotaResponse
from platform_api_python_client.rest import ApiException
from pprint import pprint

# Defining the host is optional and defaults to http://localhost
# See configuration.py for a list of all supported configuration parameters.
configuration = platform_api_python_client.Configuration(
host = "http://localhost"
)

# The client must configure the authentication and authorization parameters
# in accordance with the API server security policy.
# Examples for each auth method are provided below, use the example that
# satisfies your auth use case.

# Configure Bearer authorization: HTTPBearer
configuration = platform_api_python_client.Configuration(
access_token = os.environ["BEARER_TOKEN"]
)

# Enter a context with an instance of the API client
with platform_api_python_client.ApiClient(configuration) as api_client:
# Create an instance of the API class
api_instance = platform_api_python_client.EXTERNALApi(api_client)
cluster_id = 56 # int |
organization_id = 56 # int |

try:
# Delete Org Gpu Quota On Cluster
api_response = api_instance.delete_org_gpu_quota_on_cluster_clusters_cluster_id_organizations_organization_id_gpu_quota_delete(cluster_id, organization_id)
print("The response of EXTERNALApi->delete_org_gpu_quota_on_cluster_clusters_cluster_id_organizations_organization_id_gpu_quota_delete:\n")
pprint(api_response)
except Exception as e:
print("Exception when calling EXTERNALApi->delete_org_gpu_quota_on_cluster_clusters_cluster_id_organizations_organization_id_gpu_quota_delete: %s\n" % e)
```



### Parameters


Name | Type | Description | Notes
------------- | ------------- | ------------- | -------------
**cluster_id** | **int**| |
**organization_id** | **int**| |

### Return type

[**OrganizationGpuQuotaResponse**](OrganizationGpuQuotaResponse.md)

### Authorization

[HTTPBearer](../README.md#HTTPBearer)

### HTTP request headers

- **Content-Type**: Not defined
- **Accept**: application/json

### HTTP response details

| Status code | Description | Response headers |
|-------------|-------------|------------------|
**200** | Successful Response | - |
**422** | Validation Error | - |

[[Back to top]](#) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to Model list]](../README.md#documentation-for-models) [[Back to README]](../README.md)

# **delete_service_account_service_accounts_workos_id_delete**
> delete_service_account_service_accounts_workos_id_delete(workos_id)

Expand Down Expand Up @@ -4331,7 +4251,7 @@ This endpoint does not need any parameter.

Put Org Gpu Quota On Cluster

Persist desired organization GPU quota on this cluster. Does not apply KAI Queue CRs. ``gpu_quota`` of -1 is unlimited. Rows are never removed.
Persist organization GPU quota on this cluster and apply KAI Queue CRs. ``gpu_quota`` of -1 is unlimited; a positive value is a hard cap. Rows are never removed. Requires ``CATALOG_TARGET_REVISION`` to contain ``catalog/src/catalog/kai_gpu_queues``. A 200 means the quota row was saved and an Argo CD sync was requested (not that Queue CRs are already healthy). A 502 means the row was saved but the Application upsert/sync request failed; re-issue this idempotent PUT to retry.

### Example

Expand Down Expand Up @@ -4570,6 +4490,8 @@ This endpoint does not need any parameter.

Update Cluster

Validate a cluster component configuration for an org-owned cluster. Infra provisioning is not wired yet; ``config.components`` is validated only.

### Example

* Bearer Authentication (HTTPBearer):
Expand Down Expand Up @@ -4649,7 +4571,7 @@ Name | Type | Description | Notes

Update Cluster Metadata

Update DB metadata for an org-owned cluster. Does not drive infra stack updates. Global clusters (parent_id IS NULL) are not mutable here.
Update DB metadata for an org-owned cluster. Global clusters (parent_id IS NULL) are not mutable here.

### Example

Expand Down
2 changes: 1 addition & 1 deletion docs/GetDeploymentLogResponse.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@

Name | Type | Description | Notes
------------ | ------------- | ------------- | -------------
**events** | **List[object]** | |
**events** | **List[Dict[str, object]]** | |
**next_page_token** | **str** | | [optional]

## Example
Expand Down
6 changes: 4 additions & 2 deletions docs/GetDynamoDeploymentResponse.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
# GetDynamoDeploymentResponse

Dynamo deployment read model. ``worker_pools`` is the authoritative hardware/scaling view for both serving modes. The inherited ``hardware_instance_id`` is the single-hardware projection (worker for aggregated, decode for disaggregated) and the top-level scaling fields mirror ``worker_pools.worker``; both remain for consumers that predate ``worker_pools``.

## Properties

Expand All @@ -21,8 +22,9 @@ Name | Type | Description | Notes
**worker_pools** | [**DynamoWorkerPools**](DynamoWorkerPools.md) | | [optional]
**model** | **str** | |
**served_model_name** | **str** | | [optional]
**min_replicas** | **int** | |
**max_replicas** | **int** | |
**runtime_version** | **str** | | [optional]
**min_replicas** | **int** | Deprecated aggregated-only spelling; set this under worker_pools.worker instead. Accepted alongside worker_pools when the values agree. |
**max_replicas** | **int** | Deprecated aggregated-only spelling; set this under worker_pools.worker instead. Accepted alongside worker_pools when the values agree. |
**concurrency** | **int** | | [optional]
**cooldown_period** | **int** | | [optional]
**extra_args** | **str** | | [optional]
Expand Down
2 changes: 2 additions & 0 deletions docs/ValidationError.md
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,8 @@ Name | Type | Description | Notes
**loc** | [**List[ValidationErrorLocInner]**](ValidationErrorLocInner.md) | |
**msg** | **str** | |
**type** | **str** | |
**input** | **object** | | [optional]
**ctx** | **object** | | [optional]

## Example

Expand Down
2 changes: 1 addition & 1 deletion platform_api_python_client/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
""" # noqa: E501


__version__ = "4.28.0"
__version__ = "4.29.0"

# import apis into sdk package
from platform_api_python_client.api.external_api import EXTERNALApi
Expand Down
Loading
Loading