From a74845592d1a9cda294b48666584007cffbc92a2 Mon Sep 17 00:00:00 2001 From: platform CI Date: Thu, 12 Nov 2026 17:47:24 +0000 Subject: [PATCH] Update clients to latest platform release (4.37.0) --- README.md | 25 +- docs/CServeV2Recipe.md | 32 - docs/CreateCServeV2DeploymentResponse.md | 31 - docs/CreateCServeV3DeploymentRequest.md | 53 - docs/CreateCServeV3DeploymentResponse.md | 31 - docs/CreateDynamoDeploymentRequest.md | 2 + docs/DeploymentResponse.md | 6 +- docs/DynamoWeightTransferConfiguration.md | 30 + docs/DynamoWeightTransferPolicy.md | 10 + docs/EXTERNALApi.md | 353 ++++--- docs/GetCServeV2DeploymentResponse.md | 52 - docs/GetCServeV3DeploymentResponse.md | 58 -- docs/GetDynamoDeploymentResponse.md | 2 + platform_api_python_client/__init__.py | 10 +- .../api/external_api.py | 958 +++++++++++++++--- platform_api_python_client/api_client.py | 2 +- platform_api_python_client/configuration.py | 2 +- platform_api_python_client/models/__init__.py | 8 +- .../models/c_serve_v2_recipe.py | 109 -- .../create_c_serve_v3_deployment_request.py | 215 ---- .../create_c_serve_v3_deployment_response.py | 92 -- .../create_dynamo_deployment_request.py | 20 +- .../models/deployment_response.py | 39 +- ...> dynamo_weight_transfer_configuration.py} | 24 +- .../models/dynamo_weight_transfer_policy.py | 36 + .../get_c_serve_v2_deployment_response.py | 193 ---- .../get_c_serve_v3_deployment_response.py | 211 ---- .../models/get_dynamo_deployment_response.py | 20 +- pyproject.toml | 2 +- setup.py | 2 +- ...t_create_c_serve_v2_deployment_response.py | 56 - ...st_create_c_serve_v3_deployment_request.py | 94 -- ...t_create_c_serve_v3_deployment_response.py | 56 - test/test_create_dynamo_deployment_request.py | 3 + test/test_deployment_response.py | 12 +- ...t_dynamo_weight_transfer_configuration.py} | 27 +- test/test_dynamo_weight_transfer_policy.py | 33 + test/test_external_api.py | 33 +- ...test_get_c_serve_v2_deployment_response.py | 100 -- ...test_get_c_serve_v3_deployment_response.py | 106 -- test/test_get_dynamo_deployment_response.py | 3 + 41 files changed, 1295 insertions(+), 1856 deletions(-) delete mode 100644 docs/CServeV2Recipe.md delete mode 100644 docs/CreateCServeV2DeploymentResponse.md delete mode 100644 docs/CreateCServeV3DeploymentRequest.md delete mode 100644 docs/CreateCServeV3DeploymentResponse.md create mode 100644 docs/DynamoWeightTransferConfiguration.md create mode 100644 docs/DynamoWeightTransferPolicy.md delete mode 100644 docs/GetCServeV2DeploymentResponse.md delete mode 100644 docs/GetCServeV3DeploymentResponse.md delete mode 100644 platform_api_python_client/models/c_serve_v2_recipe.py delete mode 100644 platform_api_python_client/models/create_c_serve_v3_deployment_request.py delete mode 100644 platform_api_python_client/models/create_c_serve_v3_deployment_response.py rename platform_api_python_client/models/{create_c_serve_v2_deployment_response.py => dynamo_weight_transfer_configuration.py} (62%) create mode 100644 platform_api_python_client/models/dynamo_weight_transfer_policy.py delete mode 100644 platform_api_python_client/models/get_c_serve_v2_deployment_response.py delete mode 100644 platform_api_python_client/models/get_c_serve_v3_deployment_response.py delete mode 100644 test/test_create_c_serve_v2_deployment_response.py delete mode 100644 test/test_create_c_serve_v3_deployment_request.py delete mode 100644 test/test_create_c_serve_v3_deployment_response.py rename test/{test_c_serve_v2_recipe.py => test_dynamo_weight_transfer_configuration.py} (53%) create mode 100644 test/test_dynamo_weight_transfer_policy.py delete mode 100644 test/test_get_c_serve_v2_deployment_response.py delete mode 100644 test/test_get_c_serve_v3_deployment_response.py diff --git a/README.md b/README.md index 2d656b1..e3335bf 100644 --- a/README.md +++ b/README.md @@ -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: 4.36.0 +- Package version: 4.37.0 - Generator version: 7.9.0 - Build package: org.openapitools.codegen.languages.PythonClientCodegen @@ -96,8 +96,9 @@ Class | Method | HTTP request | Description ------------ | ------------- | ------------- | ------------- *EXTERNALApi* | [**create_cluster_clusters_post**](docs/EXTERNALApi.md#create_cluster_clusters_post) | **POST** /clusters | Create Cluster *EXTERNALApi* | [**create_compute_deployment_deployments_compute_post**](docs/EXTERNALApi.md#create_compute_deployment_deployments_compute_post) | **POST** /deployments/compute | Create Compute Deployment -*EXTERNALApi* | [**create_cserve_v2_deployment_deployments_cserve_v2_post**](docs/EXTERNALApi.md#create_cserve_v2_deployment_deployments_cserve_v2_post) | **POST** /deployments/cserve_v2 | Create Cserve V2 Deployment -*EXTERNALApi* | [**create_cserve_v3_deployment_deployments_cserve_v3_post**](docs/EXTERNALApi.md#create_cserve_v3_deployment_deployments_cserve_v3_post) | **POST** /deployments/cserve_v3 | Create Cserve V3 Deployment +*EXTERNALApi* | [**create_cserve_deployment_deployments_cserve_post**](docs/EXTERNALApi.md#create_cserve_deployment_deployments_cserve_post) | **POST** /deployments/cserve | Retired Cserve Deployment +*EXTERNALApi* | [**create_cserve_v2_deployment_deployments_cserve_v2_post**](docs/EXTERNALApi.md#create_cserve_v2_deployment_deployments_cserve_v2_post) | **POST** /deployments/cserve_v2 | Retired Cserve Deployment +*EXTERNALApi* | [**create_cserve_v3_deployment_deployments_cserve_v3_post**](docs/EXTERNALApi.md#create_cserve_v3_deployment_deployments_cserve_v3_post) | **POST** /deployments/cserve_v3 | Retired Cserve Deployment *EXTERNALApi* | [**create_dynamo_deployment_deployments_dynamo_post**](docs/EXTERNALApi.md#create_dynamo_deployment_deployments_dynamo_post) | **POST** /deployments/dynamo | Create Dynamo Deployment *EXTERNALApi* | [**create_hardware_instance_hardware_instances_post**](docs/EXTERNALApi.md#create_hardware_instance_hardware_instances_post) | **POST** /hardware-instances | Create Hardware Instance *EXTERNALApi* | [**create_inference_deployment_deployments_inference_post**](docs/EXTERNALApi.md#create_inference_deployment_deployments_inference_post) | **POST** /deployments/inference | Create Inference Deployment @@ -120,8 +121,9 @@ Class | Method | HTTP request | Description *EXTERNALApi* | [**get_clusters_clusters_get**](docs/EXTERNALApi.md#get_clusters_clusters_get) | **GET** /clusters | Get Clusters *EXTERNALApi* | [**get_compute_deployment_deployments_compute_deployment_id_get**](docs/EXTERNALApi.md#get_compute_deployment_deployments_compute_deployment_id_get) | **GET** /deployments/compute/{deployment_id} | Get Compute Deployment *EXTERNALApi* | [**get_credits_credits_get**](docs/EXTERNALApi.md#get_credits_credits_get) | **GET** /credits | Get Credits -*EXTERNALApi* | [**get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get**](docs/EXTERNALApi.md#get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get) | **GET** /deployments/cserve_v2/{deployment_id} | Get Cserve V2 Deployment -*EXTERNALApi* | [**get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get**](docs/EXTERNALApi.md#get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get) | **GET** /deployments/cserve_v3/{deployment_id} | Get Cserve V3 Deployment +*EXTERNALApi* | [**get_cserve_deployment_deployments_cserve_deployment_id_get**](docs/EXTERNALApi.md#get_cserve_deployment_deployments_cserve_deployment_id_get) | **GET** /deployments/cserve/{deployment_id} | Retired Cserve Deployment Detail +*EXTERNALApi* | [**get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get**](docs/EXTERNALApi.md#get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get) | **GET** /deployments/cserve_v2/{deployment_id} | Retired Cserve Deployment Detail +*EXTERNALApi* | [**get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get**](docs/EXTERNALApi.md#get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get) | **GET** /deployments/cserve_v3/{deployment_id} | Retired Cserve Deployment Detail *EXTERNALApi* | [**get_current_org_gpu_quota_organizations_gpu_quota_get**](docs/EXTERNALApi.md#get_current_org_gpu_quota_organizations_gpu_quota_get) | **GET** /organizations/gpu-quota | Get Current Org Gpu Quota *EXTERNALApi* | [**get_deployment_logs_deployments_logs_deployment_id_get**](docs/EXTERNALApi.md#get_deployment_logs_deployments_logs_deployment_id_get) | **GET** /deployments/logs/{deployment_id} | Get Deployment Logs *EXTERNALApi* | [**get_deployment_logs_v3_deployments_logs_v3_deployment_id_revision_number_get**](docs/EXTERNALApi.md#get_deployment_logs_v3_deployments_logs_v3_deployment_id_revision_number_get) | **GET** /deployments/logs_v3/{deployment_id}/{revision_number} | Get Deployment Logs V3 @@ -165,8 +167,9 @@ Class | Method | HTTP request | Description *EXTERNALApi* | [**update_cluster_clusters_cluster_id_put**](docs/EXTERNALApi.md#update_cluster_clusters_cluster_id_put) | **PUT** /clusters/{cluster_id} | Update Cluster *EXTERNALApi* | [**update_cluster_metadata_clusters_cluster_id_metadata_put**](docs/EXTERNALApi.md#update_cluster_metadata_clusters_cluster_id_metadata_put) | **PUT** /clusters/{cluster_id}/metadata | Update Cluster Metadata *EXTERNALApi* | [**update_compute_deployment_deployments_compute_put**](docs/EXTERNALApi.md#update_compute_deployment_deployments_compute_put) | **PUT** /deployments/compute | Update Compute Deployment -*EXTERNALApi* | [**update_cserve_v2_deployment_deployments_cserve_v2_put**](docs/EXTERNALApi.md#update_cserve_v2_deployment_deployments_cserve_v2_put) | **PUT** /deployments/cserve_v2 | Update Cserve V2 Deployment -*EXTERNALApi* | [**update_cserve_v3_deployment_deployments_cserve_v3_put**](docs/EXTERNALApi.md#update_cserve_v3_deployment_deployments_cserve_v3_put) | **PUT** /deployments/cserve_v3 | Update Cserve V3 Deployment +*EXTERNALApi* | [**update_cserve_deployment_deployments_cserve_put**](docs/EXTERNALApi.md#update_cserve_deployment_deployments_cserve_put) | **PUT** /deployments/cserve | Retired Cserve Deployment +*EXTERNALApi* | [**update_cserve_v2_deployment_deployments_cserve_v2_put**](docs/EXTERNALApi.md#update_cserve_v2_deployment_deployments_cserve_v2_put) | **PUT** /deployments/cserve_v2 | Retired Cserve Deployment +*EXTERNALApi* | [**update_cserve_v3_deployment_deployments_cserve_v3_put**](docs/EXTERNALApi.md#update_cserve_v3_deployment_deployments_cserve_v3_put) | **PUT** /deployments/cserve_v3 | Retired Cserve Deployment *EXTERNALApi* | [**update_deployment_status_deployments_status_deployment_id_put**](docs/EXTERNALApi.md#update_deployment_status_deployments_status_deployment_id_put) | **PUT** /deployments/status/{deployment_id} | Update Deployment Status *EXTERNALApi* | [**update_deployment_status_v3_deployments_status_v3_deployment_id_put**](docs/EXTERNALApi.md#update_deployment_status_v3_deployments_status_v3_deployment_id_put) | **PUT** /deployments/status_v3/{deployment_id} | Update Deployment Status V3 *EXTERNALApi* | [**update_dynamo_deployment_deployments_dynamo_put**](docs/EXTERNALApi.md#update_dynamo_deployment_deployments_dynamo_put) | **PUT** /deployments/dynamo | Update Dynamo Deployment @@ -184,7 +187,6 @@ Class | Method | HTTP request | Description - [ArgoRollouts](docs/ArgoRollouts.md) - [BackendProtocol](docs/BackendProtocol.md) - - [CServeV2Recipe](docs/CServeV2Recipe.md) - [CclDynamoPools](docs/CclDynamoPools.md) - [CclMainPools](docs/CclMainPools.md) - [CertManager](docs/CertManager.md) @@ -196,9 +198,6 @@ Class | Method | HTTP request | Description - [ClusterRegistrationRequest](docs/ClusterRegistrationRequest.md) - [ClusterRegistrationResponse](docs/ClusterRegistrationResponse.md) - [ConfigFileMount](docs/ConfigFileMount.md) - - [CreateCServeV2DeploymentResponse](docs/CreateCServeV2DeploymentResponse.md) - - [CreateCServeV3DeploymentRequest](docs/CreateCServeV3DeploymentRequest.md) - - [CreateCServeV3DeploymentResponse](docs/CreateCServeV3DeploymentResponse.md) - [CreateComputeDeploymentRequest](docs/CreateComputeDeploymentRequest.md) - [CreateComputeDeploymentResponse](docs/CreateComputeDeploymentResponse.md) - [CreateDynamoDeploymentRequest](docs/CreateDynamoDeploymentRequest.md) @@ -234,6 +233,8 @@ Class | Method | HTTP request | Description - [DynamoKvTransferConfiguration](docs/DynamoKvTransferConfiguration.md) - [DynamoKvTransferPolicy](docs/DynamoKvTransferPolicy.md) - [DynamoServingMode](docs/DynamoServingMode.md) + - [DynamoWeightTransferConfiguration](docs/DynamoWeightTransferConfiguration.md) + - [DynamoWeightTransferPolicy](docs/DynamoWeightTransferPolicy.md) - [DynamoWorkerPoolConfig](docs/DynamoWorkerPoolConfig.md) - [DynamoWorkerPools](docs/DynamoWorkerPools.md) - [Env](docs/Env.md) @@ -241,8 +242,6 @@ Class | Method | HTTP request | Description - [FinalStack](docs/FinalStack.md) - [FluentBit](docs/FluentBit.md) - [GenerateServiceAccountSecretResponse](docs/GenerateServiceAccountSecretResponse.md) - - [GetCServeV2DeploymentResponse](docs/GetCServeV2DeploymentResponse.md) - - [GetCServeV3DeploymentResponse](docs/GetCServeV3DeploymentResponse.md) - [GetClusterResponse](docs/GetClusterResponse.md) - [GetComputeDeploymentResponse](docs/GetComputeDeploymentResponse.md) - [GetDeploymentLogResponse](docs/GetDeploymentLogResponse.md) diff --git a/docs/CServeV2Recipe.md b/docs/CServeV2Recipe.md deleted file mode 100644 index a37d22d..0000000 --- a/docs/CServeV2Recipe.md +++ /dev/null @@ -1,32 +0,0 @@ -# CServeV2Recipe - -Inputs to start deployment - -## Properties - -Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- -**model** | **str** | | -**revision** | **str** | | [optional] -**is_embedding_model** | **bool** | | [optional] [default to False] - -## Example - -```python -from platform_api_python_client.models.c_serve_v2_recipe import CServeV2Recipe - -# TODO update the JSON string below -json = "{}" -# create an instance of CServeV2Recipe from a JSON string -c_serve_v2_recipe_instance = CServeV2Recipe.from_json(json) -# print the JSON string representation of the object -print(CServeV2Recipe.to_json()) - -# convert the object into a dict -c_serve_v2_recipe_dict = c_serve_v2_recipe_instance.to_dict() -# create an instance of CServeV2Recipe from a dict -c_serve_v2_recipe_from_dict = CServeV2Recipe.from_dict(c_serve_v2_recipe_dict) -``` -[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md) - - diff --git a/docs/CreateCServeV2DeploymentResponse.md b/docs/CreateCServeV2DeploymentResponse.md deleted file mode 100644 index 86facfc..0000000 --- a/docs/CreateCServeV2DeploymentResponse.md +++ /dev/null @@ -1,31 +0,0 @@ -# CreateCServeV2DeploymentResponse - - -## Properties - -Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- -**id** | **int** | | -**created_at** | **datetime** | | -**endpoint_url** | **str** | | - -## Example - -```python -from platform_api_python_client.models.create_c_serve_v2_deployment_response import CreateCServeV2DeploymentResponse - -# TODO update the JSON string below -json = "{}" -# create an instance of CreateCServeV2DeploymentResponse from a JSON string -create_c_serve_v2_deployment_response_instance = CreateCServeV2DeploymentResponse.from_json(json) -# print the JSON string representation of the object -print(CreateCServeV2DeploymentResponse.to_json()) - -# convert the object into a dict -create_c_serve_v2_deployment_response_dict = create_c_serve_v2_deployment_response_instance.to_dict() -# create an instance of CreateCServeV2DeploymentResponse from a dict -create_c_serve_v2_deployment_response_from_dict = CreateCServeV2DeploymentResponse.from_dict(create_c_serve_v2_deployment_response_dict) -``` -[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md) - - diff --git a/docs/CreateCServeV3DeploymentRequest.md b/docs/CreateCServeV3DeploymentRequest.md deleted file mode 100644 index 02b9e9a..0000000 --- a/docs/CreateCServeV3DeploymentRequest.md +++ /dev/null @@ -1,53 +0,0 @@ -# CreateCServeV3DeploymentRequest - - -## Properties - -Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- -**max_surge** | **int** | | [optional] -**max_unavailable** | **int** | | [optional] -**name** | **str** | | -**cluster_id** | **int** | | -**hardware_instance_id** | **int** | | -**user_annotations** | **Dict[str, str]** | | [optional] -**chart_revision** | **str** | | [optional] -**volume_mounts** | [**List[VolumeMount]**](VolumeMount.md) | | [optional] -**priority** | **str** | | [optional] -**hf_token_ref** | **int** | | [optional] -**recipe** | [**CServeV2Recipe**](CServeV2Recipe.md) | | -**cserve_version** | **str** | | [optional] -**hf_token** | **str** | | [optional] -**endpoint_bearer_token** | **str** | | [optional] -**bearer_token_ref** | **int** | | [optional] -**endpoint_certificate_authority** | **str** | | [optional] -**min_replicas** | **int** | | -**max_replicas** | **int** | | -**concurrency** | **int** | | [optional] -**cooldown_period** | **int** | | [optional] -**env_vars** | **Dict[str, str]** | | [optional] -**env_vars_refs** | **object** | | [optional] -**enable_logging** | **bool** | | [optional] [default to True] -**enable_node_model_cache** | **bool** | | [optional] [default to False] -**session_affinity** | **bool** | Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state. | [optional] [default to False] - -## Example - -```python -from platform_api_python_client.models.create_c_serve_v3_deployment_request import CreateCServeV3DeploymentRequest - -# TODO update the JSON string below -json = "{}" -# create an instance of CreateCServeV3DeploymentRequest from a JSON string -create_c_serve_v3_deployment_request_instance = CreateCServeV3DeploymentRequest.from_json(json) -# print the JSON string representation of the object -print(CreateCServeV3DeploymentRequest.to_json()) - -# convert the object into a dict -create_c_serve_v3_deployment_request_dict = create_c_serve_v3_deployment_request_instance.to_dict() -# create an instance of CreateCServeV3DeploymentRequest from a dict -create_c_serve_v3_deployment_request_from_dict = CreateCServeV3DeploymentRequest.from_dict(create_c_serve_v3_deployment_request_dict) -``` -[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md) - - diff --git a/docs/CreateCServeV3DeploymentResponse.md b/docs/CreateCServeV3DeploymentResponse.md deleted file mode 100644 index 57b7947..0000000 --- a/docs/CreateCServeV3DeploymentResponse.md +++ /dev/null @@ -1,31 +0,0 @@ -# CreateCServeV3DeploymentResponse - - -## Properties - -Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- -**id** | **int** | | -**created_at** | **datetime** | | -**endpoint_url** | **str** | | - -## Example - -```python -from platform_api_python_client.models.create_c_serve_v3_deployment_response import CreateCServeV3DeploymentResponse - -# TODO update the JSON string below -json = "{}" -# create an instance of CreateCServeV3DeploymentResponse from a JSON string -create_c_serve_v3_deployment_response_instance = CreateCServeV3DeploymentResponse.from_json(json) -# print the JSON string representation of the object -print(CreateCServeV3DeploymentResponse.to_json()) - -# convert the object into a dict -create_c_serve_v3_deployment_response_dict = create_c_serve_v3_deployment_response_instance.to_dict() -# create an instance of CreateCServeV3DeploymentResponse from a dict -create_c_serve_v3_deployment_response_from_dict = CreateCServeV3DeploymentResponse.from_dict(create_c_serve_v3_deployment_response_dict) -``` -[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md) - - diff --git a/docs/CreateDynamoDeploymentRequest.md b/docs/CreateDynamoDeploymentRequest.md index 8530aed..a487e19 100644 --- a/docs/CreateDynamoDeploymentRequest.md +++ b/docs/CreateDynamoDeploymentRequest.md @@ -18,7 +18,9 @@ Name | Type | Description | Notes **serving_mode** | [**DynamoServingMode**](DynamoServingMode.md) | | [optional] **worker_pools** | [**DynamoWorkerPools**](DynamoWorkerPools.md) | | [optional] **communications** | [**DynamoCommunicationsInput**](DynamoCommunicationsInput.md) | | [optional] +**weight_transfer** | [**DynamoWeightTransferConfiguration**](DynamoWeightTransferConfiguration.md) | | [optional] **model** | **str** | | +**model_revision** | **str** | | [optional] **served_model_name** | **str** | | [optional] **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. require_gpu_direct_rdma needs an EFA-capable image. Changing it restarts every component of a running deployment. | [optional] **min_replicas** | **int** | | [optional] diff --git a/docs/DeploymentResponse.md b/docs/DeploymentResponse.md index 6c2fb45..7fe11b9 100644 --- a/docs/DeploymentResponse.md +++ b/docs/DeploymentResponse.md @@ -24,7 +24,9 @@ Name | Type | Description | Notes **serving_mode** | [**DynamoServingMode**](DynamoServingMode.md) | | [optional] **worker_pools** | [**DynamoWorkerPools**](DynamoWorkerPools.md) | | [optional] **communications** | [**DynamoCommunicationsOutput**](DynamoCommunicationsOutput.md) | | [optional] +**weight_transfer** | [**DynamoWeightTransferConfiguration**](DynamoWeightTransferConfiguration.md) | | [optional] **model** | **str** | | +**model_revision** | **str** | | [optional] **served_model_name** | **str** | | [optional] **runtime_version** | **str** | | [optional] **min_replicas** | **int** | | @@ -41,9 +43,6 @@ Name | Type | Description | Notes **enable_logging** | **bool** | | [optional] [default to True] **enable_node_model_cache** | **bool** | | [optional] [default to False] **backend_protocol** | [**BackendProtocol**](BackendProtocol.md) | | [optional] -**recipe** | [**CServeV2Recipe**](CServeV2Recipe.md) | | -**cserve_version** | **str** | | [optional] -**session_affinity** | **bool** | Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state. | [optional] [default to False] **container_port** | **int** | | **healthcheck** | **str** | | [optional] **command** | **List[str]** | | [optional] @@ -51,6 +50,7 @@ Name | Type | Description | Notes **original_command** | **str** | | [optional] **image_pull_secret_credentials** | [**ImagePullSecretCredentials**](ImagePullSecretCredentials.md) | | [optional] **image_pull_secret_name** | **str** | Name of a pre-existing image pull Secret in the deployment namespace. Created, refreshed and deleted externally. Mutually exclusive with inline registry credentials and image_pull_ref. Include on updates to retain it; null clears it. | [optional] +**session_affinity** | **bool** | Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state. | [optional] [default to False] **config_file** | [**ConfigFileMount**](ConfigFileMount.md) | | [optional] **metrics** | [**MetricsConfig**](MetricsConfig.md) | | [optional] **exposed_port** | **int** | | diff --git a/docs/DynamoWeightTransferConfiguration.md b/docs/DynamoWeightTransferConfiguration.md new file mode 100644 index 0000000..1b28df0 --- /dev/null +++ b/docs/DynamoWeightTransferConfiguration.md @@ -0,0 +1,30 @@ +# DynamoWeightTransferConfiguration + +ModelExpress peer weight transfer between the workers of one pool, in either serving mode. + +## Properties + +Name | Type | Description | Notes +------------ | ------------- | ------------- | ------------- +**policy** | [**DynamoWeightTransferPolicy**](DynamoWeightTransferPolicy.md) | The default and only policy, so an empty object opts in. require_gpu_direct_rdma makes a starting worker pull the model's weights GPU to GPU from a worker of the same pool that already serves the same model_revision commit, over the cluster's GPU-direct RDMA fabric (currently AWS EFA only), instead of downloading the checkpoint. A pool's first worker, or one without a reachable peer, falls back to the usual loader. The chart and runtime image prerequisites of require_gpu_direct_rdma KV transfer apply; the API does not validate them. | [optional] + +## Example + +```python +from platform_api_python_client.models.dynamo_weight_transfer_configuration import DynamoWeightTransferConfiguration + +# TODO update the JSON string below +json = "{}" +# create an instance of DynamoWeightTransferConfiguration from a JSON string +dynamo_weight_transfer_configuration_instance = DynamoWeightTransferConfiguration.from_json(json) +# print the JSON string representation of the object +print(DynamoWeightTransferConfiguration.to_json()) + +# convert the object into a dict +dynamo_weight_transfer_configuration_dict = dynamo_weight_transfer_configuration_instance.to_dict() +# create an instance of DynamoWeightTransferConfiguration from a dict +dynamo_weight_transfer_configuration_from_dict = DynamoWeightTransferConfiguration.from_dict(dynamo_weight_transfer_configuration_dict) +``` +[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md) + + diff --git a/docs/DynamoWeightTransferPolicy.md b/docs/DynamoWeightTransferPolicy.md new file mode 100644 index 0000000..58d58cb --- /dev/null +++ b/docs/DynamoWeightTransferPolicy.md @@ -0,0 +1,10 @@ +# DynamoWeightTransferPolicy + + +## Enum + +* `REQUIRE_GPU_DIRECT_RDMA` (value: `'require_gpu_direct_rdma'`) + +[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md) + + diff --git a/docs/EXTERNALApi.md b/docs/EXTERNALApi.md index 2780840..979fb34 100644 --- a/docs/EXTERNALApi.md +++ b/docs/EXTERNALApi.md @@ -6,8 +6,9 @@ Method | HTTP request | Description ------------- | ------------- | ------------- [**create_cluster_clusters_post**](EXTERNALApi.md#create_cluster_clusters_post) | **POST** /clusters | Create Cluster [**create_compute_deployment_deployments_compute_post**](EXTERNALApi.md#create_compute_deployment_deployments_compute_post) | **POST** /deployments/compute | Create Compute Deployment -[**create_cserve_v2_deployment_deployments_cserve_v2_post**](EXTERNALApi.md#create_cserve_v2_deployment_deployments_cserve_v2_post) | **POST** /deployments/cserve_v2 | Create Cserve V2 Deployment -[**create_cserve_v3_deployment_deployments_cserve_v3_post**](EXTERNALApi.md#create_cserve_v3_deployment_deployments_cserve_v3_post) | **POST** /deployments/cserve_v3 | Create Cserve V3 Deployment +[**create_cserve_deployment_deployments_cserve_post**](EXTERNALApi.md#create_cserve_deployment_deployments_cserve_post) | **POST** /deployments/cserve | Retired Cserve Deployment +[**create_cserve_v2_deployment_deployments_cserve_v2_post**](EXTERNALApi.md#create_cserve_v2_deployment_deployments_cserve_v2_post) | **POST** /deployments/cserve_v2 | Retired Cserve Deployment +[**create_cserve_v3_deployment_deployments_cserve_v3_post**](EXTERNALApi.md#create_cserve_v3_deployment_deployments_cserve_v3_post) | **POST** /deployments/cserve_v3 | Retired Cserve Deployment [**create_dynamo_deployment_deployments_dynamo_post**](EXTERNALApi.md#create_dynamo_deployment_deployments_dynamo_post) | **POST** /deployments/dynamo | Create Dynamo Deployment [**create_hardware_instance_hardware_instances_post**](EXTERNALApi.md#create_hardware_instance_hardware_instances_post) | **POST** /hardware-instances | Create Hardware Instance [**create_inference_deployment_deployments_inference_post**](EXTERNALApi.md#create_inference_deployment_deployments_inference_post) | **POST** /deployments/inference | Create Inference Deployment @@ -30,8 +31,9 @@ Method | HTTP request | Description [**get_clusters_clusters_get**](EXTERNALApi.md#get_clusters_clusters_get) | **GET** /clusters | Get Clusters [**get_compute_deployment_deployments_compute_deployment_id_get**](EXTERNALApi.md#get_compute_deployment_deployments_compute_deployment_id_get) | **GET** /deployments/compute/{deployment_id} | Get Compute Deployment [**get_credits_credits_get**](EXTERNALApi.md#get_credits_credits_get) | **GET** /credits | Get Credits -[**get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get**](EXTERNALApi.md#get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get) | **GET** /deployments/cserve_v2/{deployment_id} | Get Cserve V2 Deployment -[**get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get**](EXTERNALApi.md#get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get) | **GET** /deployments/cserve_v3/{deployment_id} | Get Cserve V3 Deployment +[**get_cserve_deployment_deployments_cserve_deployment_id_get**](EXTERNALApi.md#get_cserve_deployment_deployments_cserve_deployment_id_get) | **GET** /deployments/cserve/{deployment_id} | Retired Cserve Deployment Detail +[**get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get**](EXTERNALApi.md#get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get) | **GET** /deployments/cserve_v2/{deployment_id} | Retired Cserve Deployment Detail +[**get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get**](EXTERNALApi.md#get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get) | **GET** /deployments/cserve_v3/{deployment_id} | Retired Cserve Deployment Detail [**get_current_org_gpu_quota_organizations_gpu_quota_get**](EXTERNALApi.md#get_current_org_gpu_quota_organizations_gpu_quota_get) | **GET** /organizations/gpu-quota | Get Current Org Gpu Quota [**get_deployment_logs_deployments_logs_deployment_id_get**](EXTERNALApi.md#get_deployment_logs_deployments_logs_deployment_id_get) | **GET** /deployments/logs/{deployment_id} | Get Deployment Logs [**get_deployment_logs_v3_deployments_logs_v3_deployment_id_revision_number_get**](EXTERNALApi.md#get_deployment_logs_v3_deployments_logs_v3_deployment_id_revision_number_get) | **GET** /deployments/logs_v3/{deployment_id}/{revision_number} | Get Deployment Logs V3 @@ -75,8 +77,9 @@ Method | HTTP request | Description [**update_cluster_clusters_cluster_id_put**](EXTERNALApi.md#update_cluster_clusters_cluster_id_put) | **PUT** /clusters/{cluster_id} | Update Cluster [**update_cluster_metadata_clusters_cluster_id_metadata_put**](EXTERNALApi.md#update_cluster_metadata_clusters_cluster_id_metadata_put) | **PUT** /clusters/{cluster_id}/metadata | Update Cluster Metadata [**update_compute_deployment_deployments_compute_put**](EXTERNALApi.md#update_compute_deployment_deployments_compute_put) | **PUT** /deployments/compute | Update Compute Deployment -[**update_cserve_v2_deployment_deployments_cserve_v2_put**](EXTERNALApi.md#update_cserve_v2_deployment_deployments_cserve_v2_put) | **PUT** /deployments/cserve_v2 | Update Cserve V2 Deployment -[**update_cserve_v3_deployment_deployments_cserve_v3_put**](EXTERNALApi.md#update_cserve_v3_deployment_deployments_cserve_v3_put) | **PUT** /deployments/cserve_v3 | Update Cserve V3 Deployment +[**update_cserve_deployment_deployments_cserve_put**](EXTERNALApi.md#update_cserve_deployment_deployments_cserve_put) | **PUT** /deployments/cserve | Retired Cserve Deployment +[**update_cserve_v2_deployment_deployments_cserve_v2_put**](EXTERNALApi.md#update_cserve_v2_deployment_deployments_cserve_v2_put) | **PUT** /deployments/cserve_v2 | Retired Cserve Deployment +[**update_cserve_v3_deployment_deployments_cserve_v3_put**](EXTERNALApi.md#update_cserve_v3_deployment_deployments_cserve_v3_put) | **PUT** /deployments/cserve_v3 | Retired Cserve Deployment [**update_deployment_status_deployments_status_deployment_id_put**](EXTERNALApi.md#update_deployment_status_deployments_status_deployment_id_put) | **PUT** /deployments/status/{deployment_id} | Update Deployment Status [**update_deployment_status_v3_deployments_status_v3_deployment_id_put**](EXTERNALApi.md#update_deployment_status_v3_deployments_status_v3_deployment_id_put) | **PUT** /deployments/status_v3/{deployment_id} | Update Deployment Status V3 [**update_dynamo_deployment_deployments_dynamo_put**](EXTERNALApi.md#update_dynamo_deployment_deployments_dynamo_put) | **PUT** /deployments/dynamo | Update Dynamo Deployment @@ -248,17 +251,16 @@ Name | Type | Description | Notes [[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) -# **create_cserve_v2_deployment_deployments_cserve_v2_post** -> CreateCServeV2DeploymentResponse create_cserve_v2_deployment_deployments_cserve_v2_post() +# **create_cserve_deployment_deployments_cserve_post** +> create_cserve_deployment_deployments_cserve_post() -Create Cserve V2 Deployment +Retired Cserve Deployment ### Example ```python import platform_api_python_client -from platform_api_python_client.models.create_c_serve_v2_deployment_response import CreateCServeV2DeploymentResponse from platform_api_python_client.rest import ApiException from pprint import pprint @@ -275,12 +277,10 @@ with platform_api_python_client.ApiClient(configuration) as api_client: api_instance = platform_api_python_client.EXTERNALApi(api_client) try: - # Create Cserve V2 Deployment - api_response = api_instance.create_cserve_v2_deployment_deployments_cserve_v2_post() - print("The response of EXTERNALApi->create_cserve_v2_deployment_deployments_cserve_v2_post:\n") - pprint(api_response) + # Retired Cserve Deployment + api_instance.create_cserve_deployment_deployments_cserve_post() except Exception as e: - print("Exception when calling EXTERNALApi->create_cserve_v2_deployment_deployments_cserve_v2_post: %s\n" % e) + print("Exception when calling EXTERNALApi->create_cserve_deployment_deployments_cserve_post: %s\n" % e) ``` @@ -291,7 +291,7 @@ This endpoint does not need any parameter. ### Return type -[**CreateCServeV2DeploymentResponse**](CreateCServeV2DeploymentResponse.md) +void (empty response body) ### Authorization @@ -306,23 +306,20 @@ No authorization required | Status code | Description | Response headers | |-------------|-------------|------------------| -**200** | Successful Response | - | +**410** | Successful Response | - | [[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) -# **create_cserve_v3_deployment_deployments_cserve_v3_post** -> CreateCServeV3DeploymentResponse create_cserve_v3_deployment_deployments_cserve_v3_post(create_c_serve_v3_deployment_request) +# **create_cserve_v2_deployment_deployments_cserve_v2_post** +> create_cserve_v2_deployment_deployments_cserve_v2_post() -Create Cserve V3 Deployment +Retired Cserve Deployment ### Example -* Bearer Authentication (HTTPBearer): ```python import platform_api_python_client -from platform_api_python_client.models.create_c_serve_v3_deployment_request import CreateCServeV3DeploymentRequest -from platform_api_python_client.models.create_c_serve_v3_deployment_response import CreateCServeV3DeploymentResponse from platform_api_python_client.rest import ApiException from pprint import pprint @@ -332,27 +329,74 @@ 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 +# 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) + + try: + # Retired Cserve Deployment + api_instance.create_cserve_v2_deployment_deployments_cserve_v2_post() + except Exception as e: + print("Exception when calling EXTERNALApi->create_cserve_v2_deployment_deployments_cserve_v2_post: %s\n" % e) +``` + + + +### Parameters + +This endpoint does not need any parameter. + +### Return type + +void (empty response body) + +### Authorization + +No authorization required + +### HTTP request headers + + - **Content-Type**: Not defined + - **Accept**: application/json + +### HTTP response details + +| Status code | Description | Response headers | +|-------------|-------------|------------------| +**410** | Successful Response | - | + +[[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) + +# **create_cserve_v3_deployment_deployments_cserve_v3_post** +> create_cserve_v3_deployment_deployments_cserve_v3_post() + +Retired Cserve Deployment + +### Example + + +```python +import platform_api_python_client +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( - access_token = os.environ["BEARER_TOKEN"] + host = "http://localhost" ) + # 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) - create_c_serve_v3_deployment_request = platform_api_python_client.CreateCServeV3DeploymentRequest() # CreateCServeV3DeploymentRequest | try: - # Create Cserve V3 Deployment - api_response = api_instance.create_cserve_v3_deployment_deployments_cserve_v3_post(create_c_serve_v3_deployment_request) - print("The response of EXTERNALApi->create_cserve_v3_deployment_deployments_cserve_v3_post:\n") - pprint(api_response) + # Retired Cserve Deployment + api_instance.create_cserve_v3_deployment_deployments_cserve_v3_post() except Exception as e: print("Exception when calling EXTERNALApi->create_cserve_v3_deployment_deployments_cserve_v3_post: %s\n" % e) ``` @@ -361,30 +405,26 @@ with platform_api_python_client.ApiClient(configuration) as api_client: ### Parameters - -Name | Type | Description | Notes -------------- | ------------- | ------------- | ------------- - **create_c_serve_v3_deployment_request** | [**CreateCServeV3DeploymentRequest**](CreateCServeV3DeploymentRequest.md)| | +This endpoint does not need any parameter. ### Return type -[**CreateCServeV3DeploymentResponse**](CreateCServeV3DeploymentResponse.md) +void (empty response body) ### Authorization -[HTTPBearer](../README.md#HTTPBearer) +No authorization required ### HTTP request headers - - **Content-Type**: application/json + - **Content-Type**: Not defined - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| -**200** | Successful Response | - | -**422** | Validation Error | - | +**410** | Successful Response | - | [[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) @@ -2057,18 +2097,16 @@ No authorization required [[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) -# **get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get** -> GetCServeV2DeploymentResponse get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get(deployment_id) +# **get_cserve_deployment_deployments_cserve_deployment_id_get** +> get_cserve_deployment_deployments_cserve_deployment_id_get(deployment_id) -Get Cserve V2 Deployment +Retired Cserve Deployment Detail ### Example -* Bearer Authentication (HTTPBearer): ```python import platform_api_python_client -from platform_api_python_client.models.get_c_serve_v2_deployment_response import GetCServeV2DeploymentResponse from platform_api_python_client.rest import ApiException from pprint import pprint @@ -2078,16 +2116,71 @@ 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 +# 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) + deployment_id = 56 # int | + + try: + # Retired Cserve Deployment Detail + api_instance.get_cserve_deployment_deployments_cserve_deployment_id_get(deployment_id) + except Exception as e: + print("Exception when calling EXTERNALApi->get_cserve_deployment_deployments_cserve_deployment_id_get: %s\n" % e) +``` + + + +### Parameters + + +Name | Type | Description | Notes +------------- | ------------- | ------------- | ------------- + **deployment_id** | **int**| | + +### Return type + +void (empty response body) + +### Authorization + +No authorization required + +### HTTP request headers + + - **Content-Type**: Not defined + - **Accept**: application/json + +### HTTP response details + +| Status code | Description | Response headers | +|-------------|-------------|------------------| +**410** | 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) + +# **get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get** +> get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get(deployment_id) + +Retired Cserve Deployment Detail + +### Example + + +```python +import platform_api_python_client +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( - access_token = os.environ["BEARER_TOKEN"] + host = "http://localhost" ) + # 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 @@ -2095,10 +2188,8 @@ with platform_api_python_client.ApiClient(configuration) as api_client: deployment_id = 56 # int | try: - # Get Cserve V2 Deployment - api_response = api_instance.get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get(deployment_id) - print("The response of EXTERNALApi->get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get:\n") - pprint(api_response) + # Retired Cserve Deployment Detail + api_instance.get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get(deployment_id) except Exception as e: print("Exception when calling EXTERNALApi->get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get: %s\n" % e) ``` @@ -2114,11 +2205,11 @@ Name | Type | Description | Notes ### Return type -[**GetCServeV2DeploymentResponse**](GetCServeV2DeploymentResponse.md) +void (empty response body) ### Authorization -[HTTPBearer](../README.md#HTTPBearer) +No authorization required ### HTTP request headers @@ -2129,23 +2220,21 @@ Name | Type | Description | Notes | Status code | Description | Response headers | |-------------|-------------|------------------| -**200** | Successful Response | - | +**410** | 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) # **get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get** -> GetCServeV3DeploymentResponse get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get(deployment_id) +> get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get(deployment_id) -Get Cserve V3 Deployment +Retired Cserve Deployment Detail ### Example -* Bearer Authentication (HTTPBearer): ```python import platform_api_python_client -from platform_api_python_client.models.get_c_serve_v3_deployment_response import GetCServeV3DeploymentResponse from platform_api_python_client.rest import ApiException from pprint import pprint @@ -2155,15 +2244,6 @@ 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: @@ -2172,10 +2252,8 @@ with platform_api_python_client.ApiClient(configuration) as api_client: deployment_id = 56 # int | try: - # Get Cserve V3 Deployment - api_response = api_instance.get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get(deployment_id) - print("The response of EXTERNALApi->get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get:\n") - pprint(api_response) + # Retired Cserve Deployment Detail + api_instance.get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get(deployment_id) except Exception as e: print("Exception when calling EXTERNALApi->get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get: %s\n" % e) ``` @@ -2191,11 +2269,11 @@ Name | Type | Description | Notes ### Return type -[**GetCServeV3DeploymentResponse**](GetCServeV3DeploymentResponse.md) +void (empty response body) ### Authorization -[HTTPBearer](../README.md#HTTPBearer) +No authorization required ### HTTP request headers @@ -2206,7 +2284,7 @@ Name | Type | Description | Notes | Status code | Description | Response headers | |-------------|-------------|------------------| -**200** | Successful Response | - | +**410** | 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) @@ -5666,17 +5744,16 @@ Name | Type | Description | Notes [[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) -# **update_cserve_v2_deployment_deployments_cserve_v2_put** -> UpdateDeploymentResponse update_cserve_v2_deployment_deployments_cserve_v2_put() +# **update_cserve_deployment_deployments_cserve_put** +> update_cserve_deployment_deployments_cserve_put() -Update Cserve V2 Deployment +Retired Cserve Deployment ### Example ```python import platform_api_python_client -from platform_api_python_client.models.update_deployment_response import UpdateDeploymentResponse from platform_api_python_client.rest import ApiException from pprint import pprint @@ -5693,12 +5770,10 @@ with platform_api_python_client.ApiClient(configuration) as api_client: api_instance = platform_api_python_client.EXTERNALApi(api_client) try: - # Update Cserve V2 Deployment - api_response = api_instance.update_cserve_v2_deployment_deployments_cserve_v2_put() - print("The response of EXTERNALApi->update_cserve_v2_deployment_deployments_cserve_v2_put:\n") - pprint(api_response) + # Retired Cserve Deployment + api_instance.update_cserve_deployment_deployments_cserve_put() except Exception as e: - print("Exception when calling EXTERNALApi->update_cserve_v2_deployment_deployments_cserve_v2_put: %s\n" % e) + print("Exception when calling EXTERNALApi->update_cserve_deployment_deployments_cserve_put: %s\n" % e) ``` @@ -5709,7 +5784,7 @@ This endpoint does not need any parameter. ### Return type -[**UpdateDeploymentResponse**](UpdateDeploymentResponse.md) +void (empty response body) ### Authorization @@ -5724,23 +5799,20 @@ No authorization required | Status code | Description | Response headers | |-------------|-------------|------------------| -**200** | Successful Response | - | +**410** | Successful Response | - | [[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) -# **update_cserve_v3_deployment_deployments_cserve_v3_put** -> UpdateDeploymentResponse update_cserve_v3_deployment_deployments_cserve_v3_put(deployment_id, create_c_serve_v3_deployment_request) +# **update_cserve_v2_deployment_deployments_cserve_v2_put** +> update_cserve_v2_deployment_deployments_cserve_v2_put() -Update Cserve V3 Deployment +Retired Cserve Deployment ### Example -* Bearer Authentication (HTTPBearer): ```python import platform_api_python_client -from platform_api_python_client.models.create_c_serve_v3_deployment_request import CreateCServeV3DeploymentRequest -from platform_api_python_client.models.update_deployment_response import UpdateDeploymentResponse from platform_api_python_client.rest import ApiException from pprint import pprint @@ -5750,28 +5822,74 @@ 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 +# 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) + + try: + # Retired Cserve Deployment + api_instance.update_cserve_v2_deployment_deployments_cserve_v2_put() + except Exception as e: + print("Exception when calling EXTERNALApi->update_cserve_v2_deployment_deployments_cserve_v2_put: %s\n" % e) +``` + + + +### Parameters + +This endpoint does not need any parameter. + +### Return type + +void (empty response body) + +### Authorization + +No authorization required + +### HTTP request headers + + - **Content-Type**: Not defined + - **Accept**: application/json + +### HTTP response details + +| Status code | Description | Response headers | +|-------------|-------------|------------------| +**410** | Successful Response | - | + +[[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) + +# **update_cserve_v3_deployment_deployments_cserve_v3_put** +> update_cserve_v3_deployment_deployments_cserve_v3_put() + +Retired Cserve Deployment + +### Example + + +```python +import platform_api_python_client +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( - access_token = os.environ["BEARER_TOKEN"] + host = "http://localhost" ) + # 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) - deployment_id = 56 # int | - create_c_serve_v3_deployment_request = platform_api_python_client.CreateCServeV3DeploymentRequest() # CreateCServeV3DeploymentRequest | try: - # Update Cserve V3 Deployment - api_response = api_instance.update_cserve_v3_deployment_deployments_cserve_v3_put(deployment_id, create_c_serve_v3_deployment_request) - print("The response of EXTERNALApi->update_cserve_v3_deployment_deployments_cserve_v3_put:\n") - pprint(api_response) + # Retired Cserve Deployment + api_instance.update_cserve_v3_deployment_deployments_cserve_v3_put() except Exception as e: print("Exception when calling EXTERNALApi->update_cserve_v3_deployment_deployments_cserve_v3_put: %s\n" % e) ``` @@ -5780,31 +5898,26 @@ with platform_api_python_client.ApiClient(configuration) as api_client: ### Parameters - -Name | Type | Description | Notes -------------- | ------------- | ------------- | ------------- - **deployment_id** | **int**| | - **create_c_serve_v3_deployment_request** | [**CreateCServeV3DeploymentRequest**](CreateCServeV3DeploymentRequest.md)| | +This endpoint does not need any parameter. ### Return type -[**UpdateDeploymentResponse**](UpdateDeploymentResponse.md) +void (empty response body) ### Authorization -[HTTPBearer](../README.md#HTTPBearer) +No authorization required ### HTTP request headers - - **Content-Type**: application/json + - **Content-Type**: Not defined - **Accept**: application/json ### HTTP response details | Status code | Description | Response headers | |-------------|-------------|------------------| -**200** | Successful Response | - | -**422** | Validation Error | - | +**410** | Successful Response | - | [[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) diff --git a/docs/GetCServeV2DeploymentResponse.md b/docs/GetCServeV2DeploymentResponse.md deleted file mode 100644 index f567521..0000000 --- a/docs/GetCServeV2DeploymentResponse.md +++ /dev/null @@ -1,52 +0,0 @@ -# GetCServeV2DeploymentResponse - - -## Properties - -Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- -**creator_email** | **str** | | -**cluster_id** | **int** | | -**id** | **int** | | -**name** | **str** | | -**endpoint_url** | **str** | | -**image_url** | **str** | | [optional] -**type** | [**DeploymentType**](DeploymentType.md) | | -**status** | [**DeploymentStatus**](DeploymentStatus.md) | | -**created_at** | **datetime** | | -**hardware_instance_id** | **int** | | -**revision_number** | **int** | | -**chart_revision** | **str** | | [optional] -**user_annotations** | **Dict[str, str]** | | [optional] -**priority** | **str** | | [optional] -**volume_mounts** | [**List[VolumeMount]**](VolumeMount.md) | | [optional] -**recipe** | [**CServeV2Recipe**](CServeV2Recipe.md) | | -**cserve_version** | **str** | | [optional] -**min_scale** | **int** | | -**max_scale** | **int** | | -**initial_scale** | **int** | | [optional] -**endpoint_certificate_authority** | **str** | | [optional] -**endpoint_bearer_token** | **str** | | [optional] -**concurrency** | **int** | | [optional] -**env_vars** | **Dict[str, str]** | | [optional] - -## Example - -```python -from platform_api_python_client.models.get_c_serve_v2_deployment_response import GetCServeV2DeploymentResponse - -# TODO update the JSON string below -json = "{}" -# create an instance of GetCServeV2DeploymentResponse from a JSON string -get_c_serve_v2_deployment_response_instance = GetCServeV2DeploymentResponse.from_json(json) -# print the JSON string representation of the object -print(GetCServeV2DeploymentResponse.to_json()) - -# convert the object into a dict -get_c_serve_v2_deployment_response_dict = get_c_serve_v2_deployment_response_instance.to_dict() -# create an instance of GetCServeV2DeploymentResponse from a dict -get_c_serve_v2_deployment_response_from_dict = GetCServeV2DeploymentResponse.from_dict(get_c_serve_v2_deployment_response_dict) -``` -[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md) - - diff --git a/docs/GetCServeV3DeploymentResponse.md b/docs/GetCServeV3DeploymentResponse.md deleted file mode 100644 index a52dc4d..0000000 --- a/docs/GetCServeV3DeploymentResponse.md +++ /dev/null @@ -1,58 +0,0 @@ -# GetCServeV3DeploymentResponse - - -## Properties - -Name | Type | Description | Notes ------------- | ------------- | ------------- | ------------- -**creator_email** | **str** | | -**cluster_id** | **int** | | -**id** | **int** | | -**name** | **str** | | -**endpoint_url** | **str** | | -**image_url** | **str** | | [optional] -**type** | [**DeploymentType**](DeploymentType.md) | | -**status** | [**DeploymentStatus**](DeploymentStatus.md) | | -**created_at** | **datetime** | | -**hardware_instance_id** | **int** | | -**revision_number** | **int** | | -**chart_revision** | **str** | | [optional] -**user_annotations** | **Dict[str, str]** | | [optional] -**priority** | **str** | | [optional] -**volume_mounts** | [**List[VolumeMount]**](VolumeMount.md) | | [optional] -**hf_token_ref** | **int** | | [optional] -**recipe** | [**CServeV2Recipe**](CServeV2Recipe.md) | | -**cserve_version** | **str** | | [optional] -**min_replicas** | **int** | | -**max_replicas** | **int** | | -**endpoint_certificate_authority** | **str** | | [optional] -**endpoint_bearer_token** | **str** | | [optional] -**concurrency** | **int** | | [optional] -**cooldown_period** | **int** | | [optional] [default to 1800] -**env_vars** | **Dict[str, str]** | | [optional] -**env_vars_refs** | **object** | | [optional] -**bearer_token_ref** | **int** | | [optional] -**enable_logging** | **bool** | | [optional] [default to True] -**enable_node_model_cache** | **bool** | | [optional] [default to False] -**session_affinity** | **bool** | Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state. | [optional] [default to False] - -## Example - -```python -from platform_api_python_client.models.get_c_serve_v3_deployment_response import GetCServeV3DeploymentResponse - -# TODO update the JSON string below -json = "{}" -# create an instance of GetCServeV3DeploymentResponse from a JSON string -get_c_serve_v3_deployment_response_instance = GetCServeV3DeploymentResponse.from_json(json) -# print the JSON string representation of the object -print(GetCServeV3DeploymentResponse.to_json()) - -# convert the object into a dict -get_c_serve_v3_deployment_response_dict = get_c_serve_v3_deployment_response_instance.to_dict() -# create an instance of GetCServeV3DeploymentResponse from a dict -get_c_serve_v3_deployment_response_from_dict = GetCServeV3DeploymentResponse.from_dict(get_c_serve_v3_deployment_response_dict) -``` -[[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md) - - diff --git a/docs/GetDynamoDeploymentResponse.md b/docs/GetDynamoDeploymentResponse.md index 72d51ef..5a4d003 100644 --- a/docs/GetDynamoDeploymentResponse.md +++ b/docs/GetDynamoDeploymentResponse.md @@ -25,7 +25,9 @@ Name | Type | Description | Notes **serving_mode** | [**DynamoServingMode**](DynamoServingMode.md) | | [optional] **worker_pools** | [**DynamoWorkerPools**](DynamoWorkerPools.md) | | [optional] **communications** | [**DynamoCommunicationsOutput**](DynamoCommunicationsOutput.md) | | [optional] +**weight_transfer** | [**DynamoWeightTransferConfiguration**](DynamoWeightTransferConfiguration.md) | | [optional] **model** | **str** | | +**model_revision** | **str** | | [optional] **served_model_name** | **str** | | [optional] **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. | diff --git a/platform_api_python_client/__init__.py b/platform_api_python_client/__init__.py index ae2d42f..3f60232 100644 --- a/platform_api_python_client/__init__.py +++ b/platform_api_python_client/__init__.py @@ -14,7 +14,7 @@ """ # noqa: E501 -__version__ = "4.36.0" +__version__ = "4.37.0" # import apis into sdk package from platform_api_python_client.api.external_api import EXTERNALApi @@ -33,7 +33,6 @@ # import models into sdk package from platform_api_python_client.models.argo_rollouts import ArgoRollouts from platform_api_python_client.models.backend_protocol import BackendProtocol -from platform_api_python_client.models.c_serve_v2_recipe import CServeV2Recipe from platform_api_python_client.models.ccl_dynamo_pools import CclDynamoPools from platform_api_python_client.models.ccl_main_pools import CclMainPools from platform_api_python_client.models.cert_manager import CertManager @@ -45,9 +44,6 @@ from platform_api_python_client.models.cluster_registration_request import ClusterRegistrationRequest from platform_api_python_client.models.cluster_registration_response import ClusterRegistrationResponse from platform_api_python_client.models.config_file_mount import ConfigFileMount -from platform_api_python_client.models.create_c_serve_v2_deployment_response import CreateCServeV2DeploymentResponse -from platform_api_python_client.models.create_c_serve_v3_deployment_request import CreateCServeV3DeploymentRequest -from platform_api_python_client.models.create_c_serve_v3_deployment_response import CreateCServeV3DeploymentResponse from platform_api_python_client.models.create_compute_deployment_request import CreateComputeDeploymentRequest from platform_api_python_client.models.create_compute_deployment_response import CreateComputeDeploymentResponse from platform_api_python_client.models.create_dynamo_deployment_request import CreateDynamoDeploymentRequest @@ -83,6 +79,8 @@ from platform_api_python_client.models.dynamo_kv_transfer_configuration import DynamoKvTransferConfiguration from platform_api_python_client.models.dynamo_kv_transfer_policy import DynamoKvTransferPolicy from platform_api_python_client.models.dynamo_serving_mode import DynamoServingMode +from platform_api_python_client.models.dynamo_weight_transfer_configuration import DynamoWeightTransferConfiguration +from platform_api_python_client.models.dynamo_weight_transfer_policy import DynamoWeightTransferPolicy from platform_api_python_client.models.dynamo_worker_pool_config import DynamoWorkerPoolConfig from platform_api_python_client.models.dynamo_worker_pools import DynamoWorkerPools from platform_api_python_client.models.env import Env @@ -90,8 +88,6 @@ from platform_api_python_client.models.final_stack import FinalStack from platform_api_python_client.models.fluent_bit import FluentBit from platform_api_python_client.models.generate_service_account_secret_response import GenerateServiceAccountSecretResponse -from platform_api_python_client.models.get_c_serve_v2_deployment_response import GetCServeV2DeploymentResponse -from platform_api_python_client.models.get_c_serve_v3_deployment_response import GetCServeV3DeploymentResponse from platform_api_python_client.models.get_cluster_response import GetClusterResponse from platform_api_python_client.models.get_compute_deployment_response import GetComputeDeploymentResponse from platform_api_python_client.models.get_deployment_log_response import GetDeploymentLogResponse diff --git a/platform_api_python_client/api/external_api.py b/platform_api_python_client/api/external_api.py index 9fd05fc..f12649b 100644 --- a/platform_api_python_client/api/external_api.py +++ b/platform_api_python_client/api/external_api.py @@ -23,9 +23,6 @@ from platform_api_python_client.models.cluster_config import ClusterConfig from platform_api_python_client.models.cluster_registration_request import ClusterRegistrationRequest from platform_api_python_client.models.cluster_registration_response import ClusterRegistrationResponse -from platform_api_python_client.models.create_c_serve_v2_deployment_response import CreateCServeV2DeploymentResponse -from platform_api_python_client.models.create_c_serve_v3_deployment_request import CreateCServeV3DeploymentRequest -from platform_api_python_client.models.create_c_serve_v3_deployment_response import CreateCServeV3DeploymentResponse from platform_api_python_client.models.create_compute_deployment_request import CreateComputeDeploymentRequest from platform_api_python_client.models.create_compute_deployment_response import CreateComputeDeploymentResponse from platform_api_python_client.models.create_dynamo_deployment_request import CreateDynamoDeploymentRequest @@ -47,8 +44,6 @@ from platform_api_python_client.models.deployment_status_v3_response import DeploymentStatusV3Response from platform_api_python_client.models.deployment_type import DeploymentType from platform_api_python_client.models.generate_service_account_secret_response import GenerateServiceAccountSecretResponse -from platform_api_python_client.models.get_c_serve_v2_deployment_response import GetCServeV2DeploymentResponse -from platform_api_python_client.models.get_c_serve_v3_deployment_response import GetCServeV3DeploymentResponse from platform_api_python_client.models.get_cluster_response import GetClusterResponse from platform_api_python_client.models.get_compute_deployment_response import GetComputeDeploymentResponse from platform_api_python_client.models.get_deployment_log_response import GetDeploymentLogResponse @@ -675,6 +670,251 @@ def _create_compute_deployment_deployments_compute_post_serialize( + @validate_call + def create_cserve_deployment_deployments_cserve_post( + self, + _request_timeout: Union[ + None, + Annotated[StrictFloat, Field(gt=0)], + Tuple[ + Annotated[StrictFloat, Field(gt=0)], + Annotated[StrictFloat, Field(gt=0)] + ] + ] = None, + _request_auth: Optional[Dict[StrictStr, Any]] = None, + _content_type: Optional[StrictStr] = None, + _headers: Optional[Dict[StrictStr, Any]] = None, + _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, + ) -> None: + """(Deprecated) Retired Cserve Deployment + + + :param _request_timeout: timeout setting for this request. If one + number provided, it will be total request + timeout. It can also be a pair (tuple) of + (connection, read) timeouts. + :type _request_timeout: int, tuple(int, int), optional + :param _request_auth: set to override the auth_settings for an a single + request; this effectively ignores the + authentication in the spec for a single request. + :type _request_auth: dict, optional + :param _content_type: force content-type for the request. + :type _content_type: str, Optional + :param _headers: set to override the headers for a single + request; this effectively ignores the headers + in the spec for a single request. + :type _headers: dict, optional + :param _host_index: set to override the host_index for a single + request; this effectively ignores the host_index + in the spec for a single request. + :type _host_index: int, optional + :return: Returns the result object. + """ # noqa: E501 + warnings.warn("POST /deployments/cserve is deprecated.", DeprecationWarning) + + _param = self._create_cserve_deployment_deployments_cserve_post_serialize( + _request_auth=_request_auth, + _content_type=_content_type, + _headers=_headers, + _host_index=_host_index + ) + + _response_types_map: Dict[str, Optional[str]] = { + '410': "object", + } + response_data = self.api_client.call_api( + *_param, + _request_timeout=_request_timeout + ) + response_data.read() + return self.api_client.response_deserialize( + response_data=response_data, + response_types_map=_response_types_map, + ).data + + + @validate_call + def create_cserve_deployment_deployments_cserve_post_with_http_info( + self, + _request_timeout: Union[ + None, + Annotated[StrictFloat, Field(gt=0)], + Tuple[ + Annotated[StrictFloat, Field(gt=0)], + Annotated[StrictFloat, Field(gt=0)] + ] + ] = None, + _request_auth: Optional[Dict[StrictStr, Any]] = None, + _content_type: Optional[StrictStr] = None, + _headers: Optional[Dict[StrictStr, Any]] = None, + _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, + ) -> ApiResponse[None]: + """(Deprecated) Retired Cserve Deployment + + + :param _request_timeout: timeout setting for this request. If one + number provided, it will be total request + timeout. It can also be a pair (tuple) of + (connection, read) timeouts. + :type _request_timeout: int, tuple(int, int), optional + :param _request_auth: set to override the auth_settings for an a single + request; this effectively ignores the + authentication in the spec for a single request. + :type _request_auth: dict, optional + :param _content_type: force content-type for the request. + :type _content_type: str, Optional + :param _headers: set to override the headers for a single + request; this effectively ignores the headers + in the spec for a single request. + :type _headers: dict, optional + :param _host_index: set to override the host_index for a single + request; this effectively ignores the host_index + in the spec for a single request. + :type _host_index: int, optional + :return: Returns the result object. + """ # noqa: E501 + warnings.warn("POST /deployments/cserve is deprecated.", DeprecationWarning) + + _param = self._create_cserve_deployment_deployments_cserve_post_serialize( + _request_auth=_request_auth, + _content_type=_content_type, + _headers=_headers, + _host_index=_host_index + ) + + _response_types_map: Dict[str, Optional[str]] = { + '410': "object", + } + response_data = self.api_client.call_api( + *_param, + _request_timeout=_request_timeout + ) + response_data.read() + return self.api_client.response_deserialize( + response_data=response_data, + response_types_map=_response_types_map, + ) + + + @validate_call + def create_cserve_deployment_deployments_cserve_post_without_preload_content( + self, + _request_timeout: Union[ + None, + Annotated[StrictFloat, Field(gt=0)], + Tuple[ + Annotated[StrictFloat, Field(gt=0)], + Annotated[StrictFloat, Field(gt=0)] + ] + ] = None, + _request_auth: Optional[Dict[StrictStr, Any]] = None, + _content_type: Optional[StrictStr] = None, + _headers: Optional[Dict[StrictStr, Any]] = None, + _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, + ) -> RESTResponseType: + """(Deprecated) Retired Cserve Deployment + + + :param _request_timeout: timeout setting for this request. If one + number provided, it will be total request + timeout. It can also be a pair (tuple) of + (connection, read) timeouts. + :type _request_timeout: int, tuple(int, int), optional + :param _request_auth: set to override the auth_settings for an a single + request; this effectively ignores the + authentication in the spec for a single request. + :type _request_auth: dict, optional + :param _content_type: force content-type for the request. + :type _content_type: str, Optional + :param _headers: set to override the headers for a single + request; this effectively ignores the headers + in the spec for a single request. + :type _headers: dict, optional + :param _host_index: set to override the host_index for a single + request; this effectively ignores the host_index + in the spec for a single request. + :type _host_index: int, optional + :return: Returns the result object. + """ # noqa: E501 + warnings.warn("POST /deployments/cserve is deprecated.", DeprecationWarning) + + _param = self._create_cserve_deployment_deployments_cserve_post_serialize( + _request_auth=_request_auth, + _content_type=_content_type, + _headers=_headers, + _host_index=_host_index + ) + + _response_types_map: Dict[str, Optional[str]] = { + '410': "object", + } + response_data = self.api_client.call_api( + *_param, + _request_timeout=_request_timeout + ) + return response_data.response + + + def _create_cserve_deployment_deployments_cserve_post_serialize( + self, + _request_auth, + _content_type, + _headers, + _host_index, + ) -> RequestSerialized: + + _host = None + + _collection_formats: Dict[str, str] = { + } + + _path_params: Dict[str, str] = {} + _query_params: List[Tuple[str, str]] = [] + _header_params: Dict[str, Optional[str]] = _headers or {} + _form_params: List[Tuple[str, str]] = [] + _files: Dict[ + str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]] + ] = {} + _body_params: Optional[bytes] = None + + # process the path parameters + # process the query parameters + # process the header parameters + # process the form parameters + # process the body parameter + + + # set the HTTP header `Accept` + if 'Accept' not in _header_params: + _header_params['Accept'] = self.api_client.select_header_accept( + [ + 'application/json' + ] + ) + + + # authentication setting + _auth_settings: List[str] = [ + ] + + return self.api_client.param_serialize( + method='POST', + resource_path='/deployments/cserve', + path_params=_path_params, + query_params=_query_params, + header_params=_header_params, + body=_body_params, + post_params=_form_params, + files=_files, + auth_settings=_auth_settings, + collection_formats=_collection_formats, + _host=_host, + _request_auth=_request_auth + ) + + + + @validate_call def create_cserve_v2_deployment_deployments_cserve_v2_post( self, @@ -690,8 +930,8 @@ def create_cserve_v2_deployment_deployments_cserve_v2_post( _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> CreateCServeV2DeploymentResponse: - """(Deprecated) Create Cserve V2 Deployment + ) -> None: + """(Deprecated) Retired Cserve Deployment :param _request_timeout: timeout setting for this request. If one @@ -725,7 +965,7 @@ def create_cserve_v2_deployment_deployments_cserve_v2_post( ) _response_types_map: Dict[str, Optional[str]] = { - '200': "CreateCServeV2DeploymentResponse", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -753,8 +993,8 @@ def create_cserve_v2_deployment_deployments_cserve_v2_post_with_http_info( _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> ApiResponse[CreateCServeV2DeploymentResponse]: - """(Deprecated) Create Cserve V2 Deployment + ) -> ApiResponse[None]: + """(Deprecated) Retired Cserve Deployment :param _request_timeout: timeout setting for this request. If one @@ -788,7 +1028,7 @@ def create_cserve_v2_deployment_deployments_cserve_v2_post_with_http_info( ) _response_types_map: Dict[str, Optional[str]] = { - '200': "CreateCServeV2DeploymentResponse", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -817,7 +1057,7 @@ def create_cserve_v2_deployment_deployments_cserve_v2_post_without_preload_conte _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, ) -> RESTResponseType: - """(Deprecated) Create Cserve V2 Deployment + """(Deprecated) Retired Cserve Deployment :param _request_timeout: timeout setting for this request. If one @@ -851,7 +1091,7 @@ def create_cserve_v2_deployment_deployments_cserve_v2_post_without_preload_conte ) _response_types_map: Dict[str, Optional[str]] = { - '200': "CreateCServeV2DeploymentResponse", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -923,7 +1163,6 @@ def _create_cserve_v2_deployment_deployments_cserve_v2_post_serialize( @validate_call def create_cserve_v3_deployment_deployments_cserve_v3_post( self, - create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest, _request_timeout: Union[ None, Annotated[StrictFloat, Field(gt=0)], @@ -936,12 +1175,10 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post( _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> CreateCServeV3DeploymentResponse: - """(Deprecated) Create Cserve V3 Deployment + ) -> None: + """(Deprecated) Retired Cserve Deployment - :param create_c_serve_v3_deployment_request: (required) - :type create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest :param _request_timeout: timeout setting for this request. If one number provided, it will be total request timeout. It can also be a pair (tuple) of @@ -966,7 +1203,6 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post( warnings.warn("POST /deployments/cserve_v3 is deprecated.", DeprecationWarning) _param = self._create_cserve_v3_deployment_deployments_cserve_v3_post_serialize( - create_c_serve_v3_deployment_request=create_c_serve_v3_deployment_request, _request_auth=_request_auth, _content_type=_content_type, _headers=_headers, @@ -974,8 +1210,7 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post( ) _response_types_map: Dict[str, Optional[str]] = { - '200': "CreateCServeV3DeploymentResponse", - '422': "HTTPValidationError", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -991,7 +1226,6 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post( @validate_call def create_cserve_v3_deployment_deployments_cserve_v3_post_with_http_info( self, - create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest, _request_timeout: Union[ None, Annotated[StrictFloat, Field(gt=0)], @@ -1004,12 +1238,10 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post_with_http_info( _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> ApiResponse[CreateCServeV3DeploymentResponse]: - """(Deprecated) Create Cserve V3 Deployment + ) -> ApiResponse[None]: + """(Deprecated) Retired Cserve Deployment - :param create_c_serve_v3_deployment_request: (required) - :type create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest :param _request_timeout: timeout setting for this request. If one number provided, it will be total request timeout. It can also be a pair (tuple) of @@ -1034,7 +1266,6 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post_with_http_info( warnings.warn("POST /deployments/cserve_v3 is deprecated.", DeprecationWarning) _param = self._create_cserve_v3_deployment_deployments_cserve_v3_post_serialize( - create_c_serve_v3_deployment_request=create_c_serve_v3_deployment_request, _request_auth=_request_auth, _content_type=_content_type, _headers=_headers, @@ -1042,8 +1273,7 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post_with_http_info( ) _response_types_map: Dict[str, Optional[str]] = { - '200': "CreateCServeV3DeploymentResponse", - '422': "HTTPValidationError", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -1059,7 +1289,6 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post_with_http_info( @validate_call def create_cserve_v3_deployment_deployments_cserve_v3_post_without_preload_content( self, - create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest, _request_timeout: Union[ None, Annotated[StrictFloat, Field(gt=0)], @@ -1073,11 +1302,9 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post_without_preload_conte _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, ) -> RESTResponseType: - """(Deprecated) Create Cserve V3 Deployment + """(Deprecated) Retired Cserve Deployment - :param create_c_serve_v3_deployment_request: (required) - :type create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest :param _request_timeout: timeout setting for this request. If one number provided, it will be total request timeout. It can also be a pair (tuple) of @@ -1102,7 +1329,6 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post_without_preload_conte warnings.warn("POST /deployments/cserve_v3 is deprecated.", DeprecationWarning) _param = self._create_cserve_v3_deployment_deployments_cserve_v3_post_serialize( - create_c_serve_v3_deployment_request=create_c_serve_v3_deployment_request, _request_auth=_request_auth, _content_type=_content_type, _headers=_headers, @@ -1110,8 +1336,7 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post_without_preload_conte ) _response_types_map: Dict[str, Optional[str]] = { - '200': "CreateCServeV3DeploymentResponse", - '422': "HTTPValidationError", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -1122,7 +1347,6 @@ def create_cserve_v3_deployment_deployments_cserve_v3_post_without_preload_conte def _create_cserve_v3_deployment_deployments_cserve_v3_post_serialize( self, - create_c_serve_v3_deployment_request, _request_auth, _content_type, _headers, @@ -1148,8 +1372,6 @@ def _create_cserve_v3_deployment_deployments_cserve_v3_post_serialize( # process the header parameters # process the form parameters # process the body parameter - if create_c_serve_v3_deployment_request is not None: - _body_params = create_c_serve_v3_deployment_request # set the HTTP header `Accept` @@ -1160,23 +1382,9 @@ def _create_cserve_v3_deployment_deployments_cserve_v3_post_serialize( ] ) - # set the HTTP header `Content-Type` - if _content_type: - _header_params['Content-Type'] = _content_type - else: - _default_content_type = ( - self.api_client.select_header_content_type( - [ - 'application/json' - ] - ) - ) - if _default_content_type is not None: - _header_params['Content-Type'] = _default_content_type # authentication setting _auth_settings: List[str] = [ - 'HTTPBearer' ] return self.api_client.param_serialize( @@ -7035,7 +7243,7 @@ def _get_credits_credits_get_serialize( @validate_call - def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get( + def get_cserve_deployment_deployments_cserve_deployment_id_get( self, deployment_id: StrictInt, _request_timeout: Union[ @@ -7050,8 +7258,8 @@ def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get( _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> GetCServeV2DeploymentResponse: - """Get Cserve V2 Deployment + ) -> None: + """(Deprecated) Retired Cserve Deployment Detail :param deployment_id: (required) @@ -7077,8 +7285,9 @@ def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get( :type _host_index: int, optional :return: Returns the result object. """ # noqa: E501 + warnings.warn("GET /deployments/cserve/{deployment_id} is deprecated.", DeprecationWarning) - _param = self._get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_serialize( + _param = self._get_cserve_deployment_deployments_cserve_deployment_id_get_serialize( deployment_id=deployment_id, _request_auth=_request_auth, _content_type=_content_type, @@ -7087,7 +7296,7 @@ def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get( ) _response_types_map: Dict[str, Optional[str]] = { - '200': "GetCServeV2DeploymentResponse", + '410': "object", '422': "HTTPValidationError", } response_data = self.api_client.call_api( @@ -7102,7 +7311,7 @@ def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get( @validate_call - def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_with_http_info( + def get_cserve_deployment_deployments_cserve_deployment_id_get_with_http_info( self, deployment_id: StrictInt, _request_timeout: Union[ @@ -7117,8 +7326,8 @@ def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_with_http_i _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> ApiResponse[GetCServeV2DeploymentResponse]: - """Get Cserve V2 Deployment + ) -> ApiResponse[None]: + """(Deprecated) Retired Cserve Deployment Detail :param deployment_id: (required) @@ -7144,8 +7353,9 @@ def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_with_http_i :type _host_index: int, optional :return: Returns the result object. """ # noqa: E501 + warnings.warn("GET /deployments/cserve/{deployment_id} is deprecated.", DeprecationWarning) - _param = self._get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_serialize( + _param = self._get_cserve_deployment_deployments_cserve_deployment_id_get_serialize( deployment_id=deployment_id, _request_auth=_request_auth, _content_type=_content_type, @@ -7154,7 +7364,7 @@ def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_with_http_i ) _response_types_map: Dict[str, Optional[str]] = { - '200': "GetCServeV2DeploymentResponse", + '410': "object", '422': "HTTPValidationError", } response_data = self.api_client.call_api( @@ -7169,7 +7379,7 @@ def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_with_http_i @validate_call - def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_without_preload_content( + def get_cserve_deployment_deployments_cserve_deployment_id_get_without_preload_content( self, deployment_id: StrictInt, _request_timeout: Union[ @@ -7185,7 +7395,7 @@ def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_without_pre _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, ) -> RESTResponseType: - """Get Cserve V2 Deployment + """(Deprecated) Retired Cserve Deployment Detail :param deployment_id: (required) @@ -7211,6 +7421,270 @@ def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_without_pre :type _host_index: int, optional :return: Returns the result object. """ # noqa: E501 + warnings.warn("GET /deployments/cserve/{deployment_id} is deprecated.", DeprecationWarning) + + _param = self._get_cserve_deployment_deployments_cserve_deployment_id_get_serialize( + deployment_id=deployment_id, + _request_auth=_request_auth, + _content_type=_content_type, + _headers=_headers, + _host_index=_host_index + ) + + _response_types_map: Dict[str, Optional[str]] = { + '410': "object", + '422': "HTTPValidationError", + } + response_data = self.api_client.call_api( + *_param, + _request_timeout=_request_timeout + ) + return response_data.response + + + def _get_cserve_deployment_deployments_cserve_deployment_id_get_serialize( + self, + deployment_id, + _request_auth, + _content_type, + _headers, + _host_index, + ) -> RequestSerialized: + + _host = None + + _collection_formats: Dict[str, str] = { + } + + _path_params: Dict[str, str] = {} + _query_params: List[Tuple[str, str]] = [] + _header_params: Dict[str, Optional[str]] = _headers or {} + _form_params: List[Tuple[str, str]] = [] + _files: Dict[ + str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]] + ] = {} + _body_params: Optional[bytes] = None + + # process the path parameters + if deployment_id is not None: + _path_params['deployment_id'] = deployment_id + # process the query parameters + # process the header parameters + # process the form parameters + # process the body parameter + + + # set the HTTP header `Accept` + if 'Accept' not in _header_params: + _header_params['Accept'] = self.api_client.select_header_accept( + [ + 'application/json' + ] + ) + + + # authentication setting + _auth_settings: List[str] = [ + ] + + return self.api_client.param_serialize( + method='GET', + resource_path='/deployments/cserve/{deployment_id}', + path_params=_path_params, + query_params=_query_params, + header_params=_header_params, + body=_body_params, + post_params=_form_params, + files=_files, + auth_settings=_auth_settings, + collection_formats=_collection_formats, + _host=_host, + _request_auth=_request_auth + ) + + + + + @validate_call + def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get( + self, + deployment_id: StrictInt, + _request_timeout: Union[ + None, + Annotated[StrictFloat, Field(gt=0)], + Tuple[ + Annotated[StrictFloat, Field(gt=0)], + Annotated[StrictFloat, Field(gt=0)] + ] + ] = None, + _request_auth: Optional[Dict[StrictStr, Any]] = None, + _content_type: Optional[StrictStr] = None, + _headers: Optional[Dict[StrictStr, Any]] = None, + _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, + ) -> None: + """(Deprecated) Retired Cserve Deployment Detail + + + :param deployment_id: (required) + :type deployment_id: int + :param _request_timeout: timeout setting for this request. If one + number provided, it will be total request + timeout. It can also be a pair (tuple) of + (connection, read) timeouts. + :type _request_timeout: int, tuple(int, int), optional + :param _request_auth: set to override the auth_settings for an a single + request; this effectively ignores the + authentication in the spec for a single request. + :type _request_auth: dict, optional + :param _content_type: force content-type for the request. + :type _content_type: str, Optional + :param _headers: set to override the headers for a single + request; this effectively ignores the headers + in the spec for a single request. + :type _headers: dict, optional + :param _host_index: set to override the host_index for a single + request; this effectively ignores the host_index + in the spec for a single request. + :type _host_index: int, optional + :return: Returns the result object. + """ # noqa: E501 + warnings.warn("GET /deployments/cserve_v2/{deployment_id} is deprecated.", DeprecationWarning) + + _param = self._get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_serialize( + deployment_id=deployment_id, + _request_auth=_request_auth, + _content_type=_content_type, + _headers=_headers, + _host_index=_host_index + ) + + _response_types_map: Dict[str, Optional[str]] = { + '410': "object", + '422': "HTTPValidationError", + } + response_data = self.api_client.call_api( + *_param, + _request_timeout=_request_timeout + ) + response_data.read() + return self.api_client.response_deserialize( + response_data=response_data, + response_types_map=_response_types_map, + ).data + + + @validate_call + def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_with_http_info( + self, + deployment_id: StrictInt, + _request_timeout: Union[ + None, + Annotated[StrictFloat, Field(gt=0)], + Tuple[ + Annotated[StrictFloat, Field(gt=0)], + Annotated[StrictFloat, Field(gt=0)] + ] + ] = None, + _request_auth: Optional[Dict[StrictStr, Any]] = None, + _content_type: Optional[StrictStr] = None, + _headers: Optional[Dict[StrictStr, Any]] = None, + _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, + ) -> ApiResponse[None]: + """(Deprecated) Retired Cserve Deployment Detail + + + :param deployment_id: (required) + :type deployment_id: int + :param _request_timeout: timeout setting for this request. If one + number provided, it will be total request + timeout. It can also be a pair (tuple) of + (connection, read) timeouts. + :type _request_timeout: int, tuple(int, int), optional + :param _request_auth: set to override the auth_settings for an a single + request; this effectively ignores the + authentication in the spec for a single request. + :type _request_auth: dict, optional + :param _content_type: force content-type for the request. + :type _content_type: str, Optional + :param _headers: set to override the headers for a single + request; this effectively ignores the headers + in the spec for a single request. + :type _headers: dict, optional + :param _host_index: set to override the host_index for a single + request; this effectively ignores the host_index + in the spec for a single request. + :type _host_index: int, optional + :return: Returns the result object. + """ # noqa: E501 + warnings.warn("GET /deployments/cserve_v2/{deployment_id} is deprecated.", DeprecationWarning) + + _param = self._get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_serialize( + deployment_id=deployment_id, + _request_auth=_request_auth, + _content_type=_content_type, + _headers=_headers, + _host_index=_host_index + ) + + _response_types_map: Dict[str, Optional[str]] = { + '410': "object", + '422': "HTTPValidationError", + } + response_data = self.api_client.call_api( + *_param, + _request_timeout=_request_timeout + ) + response_data.read() + return self.api_client.response_deserialize( + response_data=response_data, + response_types_map=_response_types_map, + ) + + + @validate_call + def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_without_preload_content( + self, + deployment_id: StrictInt, + _request_timeout: Union[ + None, + Annotated[StrictFloat, Field(gt=0)], + Tuple[ + Annotated[StrictFloat, Field(gt=0)], + Annotated[StrictFloat, Field(gt=0)] + ] + ] = None, + _request_auth: Optional[Dict[StrictStr, Any]] = None, + _content_type: Optional[StrictStr] = None, + _headers: Optional[Dict[StrictStr, Any]] = None, + _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, + ) -> RESTResponseType: + """(Deprecated) Retired Cserve Deployment Detail + + + :param deployment_id: (required) + :type deployment_id: int + :param _request_timeout: timeout setting for this request. If one + number provided, it will be total request + timeout. It can also be a pair (tuple) of + (connection, read) timeouts. + :type _request_timeout: int, tuple(int, int), optional + :param _request_auth: set to override the auth_settings for an a single + request; this effectively ignores the + authentication in the spec for a single request. + :type _request_auth: dict, optional + :param _content_type: force content-type for the request. + :type _content_type: str, Optional + :param _headers: set to override the headers for a single + request; this effectively ignores the headers + in the spec for a single request. + :type _headers: dict, optional + :param _host_index: set to override the host_index for a single + request; this effectively ignores the host_index + in the spec for a single request. + :type _host_index: int, optional + :return: Returns the result object. + """ # noqa: E501 + warnings.warn("GET /deployments/cserve_v2/{deployment_id} is deprecated.", DeprecationWarning) _param = self._get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_serialize( deployment_id=deployment_id, @@ -7221,7 +7695,7 @@ def get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_without_pre ) _response_types_map: Dict[str, Optional[str]] = { - '200': "GetCServeV2DeploymentResponse", + '410': "object", '422': "HTTPValidationError", } response_data = self.api_client.call_api( @@ -7274,7 +7748,6 @@ def _get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get_serialize( # authentication setting _auth_settings: List[str] = [ - 'HTTPBearer' ] return self.api_client.param_serialize( @@ -7311,8 +7784,8 @@ def get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get( _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> GetCServeV3DeploymentResponse: - """Get Cserve V3 Deployment + ) -> None: + """(Deprecated) Retired Cserve Deployment Detail :param deployment_id: (required) @@ -7338,6 +7811,7 @@ def get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get( :type _host_index: int, optional :return: Returns the result object. """ # noqa: E501 + warnings.warn("GET /deployments/cserve_v3/{deployment_id} is deprecated.", DeprecationWarning) _param = self._get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get_serialize( deployment_id=deployment_id, @@ -7348,7 +7822,7 @@ def get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get( ) _response_types_map: Dict[str, Optional[str]] = { - '200': "GetCServeV3DeploymentResponse", + '410': "object", '422': "HTTPValidationError", } response_data = self.api_client.call_api( @@ -7378,8 +7852,8 @@ def get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get_with_http_i _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> ApiResponse[GetCServeV3DeploymentResponse]: - """Get Cserve V3 Deployment + ) -> ApiResponse[None]: + """(Deprecated) Retired Cserve Deployment Detail :param deployment_id: (required) @@ -7405,6 +7879,7 @@ def get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get_with_http_i :type _host_index: int, optional :return: Returns the result object. """ # noqa: E501 + warnings.warn("GET /deployments/cserve_v3/{deployment_id} is deprecated.", DeprecationWarning) _param = self._get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get_serialize( deployment_id=deployment_id, @@ -7415,7 +7890,7 @@ def get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get_with_http_i ) _response_types_map: Dict[str, Optional[str]] = { - '200': "GetCServeV3DeploymentResponse", + '410': "object", '422': "HTTPValidationError", } response_data = self.api_client.call_api( @@ -7446,7 +7921,7 @@ def get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get_without_pre _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, ) -> RESTResponseType: - """Get Cserve V3 Deployment + """(Deprecated) Retired Cserve Deployment Detail :param deployment_id: (required) @@ -7472,6 +7947,7 @@ def get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get_without_pre :type _host_index: int, optional :return: Returns the result object. """ # noqa: E501 + warnings.warn("GET /deployments/cserve_v3/{deployment_id} is deprecated.", DeprecationWarning) _param = self._get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get_serialize( deployment_id=deployment_id, @@ -7482,7 +7958,7 @@ def get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get_without_pre ) _response_types_map: Dict[str, Optional[str]] = { - '200': "GetCServeV3DeploymentResponse", + '410': "object", '422': "HTTPValidationError", } response_data = self.api_client.call_api( @@ -7535,7 +8011,6 @@ def _get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get_serialize( # authentication setting _auth_settings: List[str] = [ - 'HTTPBearer' ] return self.api_client.param_serialize( @@ -19869,7 +20344,7 @@ def _update_compute_deployment_deployments_compute_put_serialize( @validate_call - def update_cserve_v2_deployment_deployments_cserve_v2_put( + def update_cserve_deployment_deployments_cserve_put( self, _request_timeout: Union[ None, @@ -19883,8 +20358,253 @@ def update_cserve_v2_deployment_deployments_cserve_v2_put( _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> UpdateDeploymentResponse: - """(Deprecated) Update Cserve V2 Deployment + ) -> None: + """(Deprecated) Retired Cserve Deployment + + + :param _request_timeout: timeout setting for this request. If one + number provided, it will be total request + timeout. It can also be a pair (tuple) of + (connection, read) timeouts. + :type _request_timeout: int, tuple(int, int), optional + :param _request_auth: set to override the auth_settings for an a single + request; this effectively ignores the + authentication in the spec for a single request. + :type _request_auth: dict, optional + :param _content_type: force content-type for the request. + :type _content_type: str, Optional + :param _headers: set to override the headers for a single + request; this effectively ignores the headers + in the spec for a single request. + :type _headers: dict, optional + :param _host_index: set to override the host_index for a single + request; this effectively ignores the host_index + in the spec for a single request. + :type _host_index: int, optional + :return: Returns the result object. + """ # noqa: E501 + warnings.warn("PUT /deployments/cserve is deprecated.", DeprecationWarning) + + _param = self._update_cserve_deployment_deployments_cserve_put_serialize( + _request_auth=_request_auth, + _content_type=_content_type, + _headers=_headers, + _host_index=_host_index + ) + + _response_types_map: Dict[str, Optional[str]] = { + '410': "object", + } + response_data = self.api_client.call_api( + *_param, + _request_timeout=_request_timeout + ) + response_data.read() + return self.api_client.response_deserialize( + response_data=response_data, + response_types_map=_response_types_map, + ).data + + + @validate_call + def update_cserve_deployment_deployments_cserve_put_with_http_info( + self, + _request_timeout: Union[ + None, + Annotated[StrictFloat, Field(gt=0)], + Tuple[ + Annotated[StrictFloat, Field(gt=0)], + Annotated[StrictFloat, Field(gt=0)] + ] + ] = None, + _request_auth: Optional[Dict[StrictStr, Any]] = None, + _content_type: Optional[StrictStr] = None, + _headers: Optional[Dict[StrictStr, Any]] = None, + _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, + ) -> ApiResponse[None]: + """(Deprecated) Retired Cserve Deployment + + + :param _request_timeout: timeout setting for this request. If one + number provided, it will be total request + timeout. It can also be a pair (tuple) of + (connection, read) timeouts. + :type _request_timeout: int, tuple(int, int), optional + :param _request_auth: set to override the auth_settings for an a single + request; this effectively ignores the + authentication in the spec for a single request. + :type _request_auth: dict, optional + :param _content_type: force content-type for the request. + :type _content_type: str, Optional + :param _headers: set to override the headers for a single + request; this effectively ignores the headers + in the spec for a single request. + :type _headers: dict, optional + :param _host_index: set to override the host_index for a single + request; this effectively ignores the host_index + in the spec for a single request. + :type _host_index: int, optional + :return: Returns the result object. + """ # noqa: E501 + warnings.warn("PUT /deployments/cserve is deprecated.", DeprecationWarning) + + _param = self._update_cserve_deployment_deployments_cserve_put_serialize( + _request_auth=_request_auth, + _content_type=_content_type, + _headers=_headers, + _host_index=_host_index + ) + + _response_types_map: Dict[str, Optional[str]] = { + '410': "object", + } + response_data = self.api_client.call_api( + *_param, + _request_timeout=_request_timeout + ) + response_data.read() + return self.api_client.response_deserialize( + response_data=response_data, + response_types_map=_response_types_map, + ) + + + @validate_call + def update_cserve_deployment_deployments_cserve_put_without_preload_content( + self, + _request_timeout: Union[ + None, + Annotated[StrictFloat, Field(gt=0)], + Tuple[ + Annotated[StrictFloat, Field(gt=0)], + Annotated[StrictFloat, Field(gt=0)] + ] + ] = None, + _request_auth: Optional[Dict[StrictStr, Any]] = None, + _content_type: Optional[StrictStr] = None, + _headers: Optional[Dict[StrictStr, Any]] = None, + _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, + ) -> RESTResponseType: + """(Deprecated) Retired Cserve Deployment + + + :param _request_timeout: timeout setting for this request. If one + number provided, it will be total request + timeout. It can also be a pair (tuple) of + (connection, read) timeouts. + :type _request_timeout: int, tuple(int, int), optional + :param _request_auth: set to override the auth_settings for an a single + request; this effectively ignores the + authentication in the spec for a single request. + :type _request_auth: dict, optional + :param _content_type: force content-type for the request. + :type _content_type: str, Optional + :param _headers: set to override the headers for a single + request; this effectively ignores the headers + in the spec for a single request. + :type _headers: dict, optional + :param _host_index: set to override the host_index for a single + request; this effectively ignores the host_index + in the spec for a single request. + :type _host_index: int, optional + :return: Returns the result object. + """ # noqa: E501 + warnings.warn("PUT /deployments/cserve is deprecated.", DeprecationWarning) + + _param = self._update_cserve_deployment_deployments_cserve_put_serialize( + _request_auth=_request_auth, + _content_type=_content_type, + _headers=_headers, + _host_index=_host_index + ) + + _response_types_map: Dict[str, Optional[str]] = { + '410': "object", + } + response_data = self.api_client.call_api( + *_param, + _request_timeout=_request_timeout + ) + return response_data.response + + + def _update_cserve_deployment_deployments_cserve_put_serialize( + self, + _request_auth, + _content_type, + _headers, + _host_index, + ) -> RequestSerialized: + + _host = None + + _collection_formats: Dict[str, str] = { + } + + _path_params: Dict[str, str] = {} + _query_params: List[Tuple[str, str]] = [] + _header_params: Dict[str, Optional[str]] = _headers or {} + _form_params: List[Tuple[str, str]] = [] + _files: Dict[ + str, Union[str, bytes, List[str], List[bytes], List[Tuple[str, bytes]]] + ] = {} + _body_params: Optional[bytes] = None + + # process the path parameters + # process the query parameters + # process the header parameters + # process the form parameters + # process the body parameter + + + # set the HTTP header `Accept` + if 'Accept' not in _header_params: + _header_params['Accept'] = self.api_client.select_header_accept( + [ + 'application/json' + ] + ) + + + # authentication setting + _auth_settings: List[str] = [ + ] + + return self.api_client.param_serialize( + method='PUT', + resource_path='/deployments/cserve', + path_params=_path_params, + query_params=_query_params, + header_params=_header_params, + body=_body_params, + post_params=_form_params, + files=_files, + auth_settings=_auth_settings, + collection_formats=_collection_formats, + _host=_host, + _request_auth=_request_auth + ) + + + + + @validate_call + def update_cserve_v2_deployment_deployments_cserve_v2_put( + self, + _request_timeout: Union[ + None, + Annotated[StrictFloat, Field(gt=0)], + Tuple[ + Annotated[StrictFloat, Field(gt=0)], + Annotated[StrictFloat, Field(gt=0)] + ] + ] = None, + _request_auth: Optional[Dict[StrictStr, Any]] = None, + _content_type: Optional[StrictStr] = None, + _headers: Optional[Dict[StrictStr, Any]] = None, + _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, + ) -> None: + """(Deprecated) Retired Cserve Deployment :param _request_timeout: timeout setting for this request. If one @@ -19918,7 +20638,7 @@ def update_cserve_v2_deployment_deployments_cserve_v2_put( ) _response_types_map: Dict[str, Optional[str]] = { - '200': "UpdateDeploymentResponse", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -19946,8 +20666,8 @@ def update_cserve_v2_deployment_deployments_cserve_v2_put_with_http_info( _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> ApiResponse[UpdateDeploymentResponse]: - """(Deprecated) Update Cserve V2 Deployment + ) -> ApiResponse[None]: + """(Deprecated) Retired Cserve Deployment :param _request_timeout: timeout setting for this request. If one @@ -19981,7 +20701,7 @@ def update_cserve_v2_deployment_deployments_cserve_v2_put_with_http_info( ) _response_types_map: Dict[str, Optional[str]] = { - '200': "UpdateDeploymentResponse", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -20010,7 +20730,7 @@ def update_cserve_v2_deployment_deployments_cserve_v2_put_without_preload_conten _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, ) -> RESTResponseType: - """(Deprecated) Update Cserve V2 Deployment + """(Deprecated) Retired Cserve Deployment :param _request_timeout: timeout setting for this request. If one @@ -20044,7 +20764,7 @@ def update_cserve_v2_deployment_deployments_cserve_v2_put_without_preload_conten ) _response_types_map: Dict[str, Optional[str]] = { - '200': "UpdateDeploymentResponse", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -20116,8 +20836,6 @@ def _update_cserve_v2_deployment_deployments_cserve_v2_put_serialize( @validate_call def update_cserve_v3_deployment_deployments_cserve_v3_put( self, - deployment_id: StrictInt, - create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest, _request_timeout: Union[ None, Annotated[StrictFloat, Field(gt=0)], @@ -20130,14 +20848,10 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put( _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> UpdateDeploymentResponse: - """Update Cserve V3 Deployment + ) -> None: + """(Deprecated) Retired Cserve Deployment - :param deployment_id: (required) - :type deployment_id: int - :param create_c_serve_v3_deployment_request: (required) - :type create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest :param _request_timeout: timeout setting for this request. If one number provided, it will be total request timeout. It can also be a pair (tuple) of @@ -20159,10 +20873,9 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put( :type _host_index: int, optional :return: Returns the result object. """ # noqa: E501 + warnings.warn("PUT /deployments/cserve_v3 is deprecated.", DeprecationWarning) _param = self._update_cserve_v3_deployment_deployments_cserve_v3_put_serialize( - deployment_id=deployment_id, - create_c_serve_v3_deployment_request=create_c_serve_v3_deployment_request, _request_auth=_request_auth, _content_type=_content_type, _headers=_headers, @@ -20170,8 +20883,7 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put( ) _response_types_map: Dict[str, Optional[str]] = { - '200': "UpdateDeploymentResponse", - '422': "HTTPValidationError", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -20187,8 +20899,6 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put( @validate_call def update_cserve_v3_deployment_deployments_cserve_v3_put_with_http_info( self, - deployment_id: StrictInt, - create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest, _request_timeout: Union[ None, Annotated[StrictFloat, Field(gt=0)], @@ -20201,14 +20911,10 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put_with_http_info( _content_type: Optional[StrictStr] = None, _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, - ) -> ApiResponse[UpdateDeploymentResponse]: - """Update Cserve V3 Deployment + ) -> ApiResponse[None]: + """(Deprecated) Retired Cserve Deployment - :param deployment_id: (required) - :type deployment_id: int - :param create_c_serve_v3_deployment_request: (required) - :type create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest :param _request_timeout: timeout setting for this request. If one number provided, it will be total request timeout. It can also be a pair (tuple) of @@ -20230,10 +20936,9 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put_with_http_info( :type _host_index: int, optional :return: Returns the result object. """ # noqa: E501 + warnings.warn("PUT /deployments/cserve_v3 is deprecated.", DeprecationWarning) _param = self._update_cserve_v3_deployment_deployments_cserve_v3_put_serialize( - deployment_id=deployment_id, - create_c_serve_v3_deployment_request=create_c_serve_v3_deployment_request, _request_auth=_request_auth, _content_type=_content_type, _headers=_headers, @@ -20241,8 +20946,7 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put_with_http_info( ) _response_types_map: Dict[str, Optional[str]] = { - '200': "UpdateDeploymentResponse", - '422': "HTTPValidationError", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -20258,8 +20962,6 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put_with_http_info( @validate_call def update_cserve_v3_deployment_deployments_cserve_v3_put_without_preload_content( self, - deployment_id: StrictInt, - create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest, _request_timeout: Union[ None, Annotated[StrictFloat, Field(gt=0)], @@ -20273,13 +20975,9 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put_without_preload_conten _headers: Optional[Dict[StrictStr, Any]] = None, _host_index: Annotated[StrictInt, Field(ge=0, le=0)] = 0, ) -> RESTResponseType: - """Update Cserve V3 Deployment + """(Deprecated) Retired Cserve Deployment - :param deployment_id: (required) - :type deployment_id: int - :param create_c_serve_v3_deployment_request: (required) - :type create_c_serve_v3_deployment_request: CreateCServeV3DeploymentRequest :param _request_timeout: timeout setting for this request. If one number provided, it will be total request timeout. It can also be a pair (tuple) of @@ -20301,10 +20999,9 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put_without_preload_conten :type _host_index: int, optional :return: Returns the result object. """ # noqa: E501 + warnings.warn("PUT /deployments/cserve_v3 is deprecated.", DeprecationWarning) _param = self._update_cserve_v3_deployment_deployments_cserve_v3_put_serialize( - deployment_id=deployment_id, - create_c_serve_v3_deployment_request=create_c_serve_v3_deployment_request, _request_auth=_request_auth, _content_type=_content_type, _headers=_headers, @@ -20312,8 +21009,7 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put_without_preload_conten ) _response_types_map: Dict[str, Optional[str]] = { - '200': "UpdateDeploymentResponse", - '422': "HTTPValidationError", + '410': "object", } response_data = self.api_client.call_api( *_param, @@ -20324,8 +21020,6 @@ def update_cserve_v3_deployment_deployments_cserve_v3_put_without_preload_conten def _update_cserve_v3_deployment_deployments_cserve_v3_put_serialize( self, - deployment_id, - create_c_serve_v3_deployment_request, _request_auth, _content_type, _headers, @@ -20348,15 +21042,9 @@ def _update_cserve_v3_deployment_deployments_cserve_v3_put_serialize( # process the path parameters # process the query parameters - if deployment_id is not None: - - _query_params.append(('deployment_id', deployment_id)) - # process the header parameters # process the form parameters # process the body parameter - if create_c_serve_v3_deployment_request is not None: - _body_params = create_c_serve_v3_deployment_request # set the HTTP header `Accept` @@ -20367,23 +21055,9 @@ def _update_cserve_v3_deployment_deployments_cserve_v3_put_serialize( ] ) - # set the HTTP header `Content-Type` - if _content_type: - _header_params['Content-Type'] = _content_type - else: - _default_content_type = ( - self.api_client.select_header_content_type( - [ - 'application/json' - ] - ) - ) - if _default_content_type is not None: - _header_params['Content-Type'] = _default_content_type # authentication setting _auth_settings: List[str] = [ - 'HTTPBearer' ] return self.api_client.param_serialize( diff --git a/platform_api_python_client/api_client.py b/platform_api_python_client/api_client.py index 22b660e..43d5b7b 100644 --- a/platform_api_python_client/api_client.py +++ b/platform_api_python_client/api_client.py @@ -90,7 +90,7 @@ def __init__( self.default_headers[header_name] = header_value self.cookie = cookie # Set default User-Agent. - self.user_agent = 'OpenAPI-Generator/4.36.0/python' + self.user_agent = 'OpenAPI-Generator/4.37.0/python' self.client_side_validation = configuration.client_side_validation def __enter__(self): diff --git a/platform_api_python_client/configuration.py b/platform_api_python_client/configuration.py index 2f87e14..b368cf2 100644 --- a/platform_api_python_client/configuration.py +++ b/platform_api_python_client/configuration.py @@ -392,7 +392,7 @@ def to_debug_report(self): "OS: {env}\n"\ "Python Version: {pyversion}\n"\ "Version of the API: 0.1.0\n"\ - "SDK Package Version: 4.36.0".\ + "SDK Package Version: 4.37.0".\ format(env=sys.platform, pyversion=sys.version) def get_host_settings(self): diff --git a/platform_api_python_client/models/__init__.py b/platform_api_python_client/models/__init__.py index 60df486..5273003 100644 --- a/platform_api_python_client/models/__init__.py +++ b/platform_api_python_client/models/__init__.py @@ -16,7 +16,6 @@ # import models into model package from platform_api_python_client.models.argo_rollouts import ArgoRollouts from platform_api_python_client.models.backend_protocol import BackendProtocol -from platform_api_python_client.models.c_serve_v2_recipe import CServeV2Recipe from platform_api_python_client.models.ccl_dynamo_pools import CclDynamoPools from platform_api_python_client.models.ccl_main_pools import CclMainPools from platform_api_python_client.models.cert_manager import CertManager @@ -28,9 +27,6 @@ from platform_api_python_client.models.cluster_registration_request import ClusterRegistrationRequest from platform_api_python_client.models.cluster_registration_response import ClusterRegistrationResponse from platform_api_python_client.models.config_file_mount import ConfigFileMount -from platform_api_python_client.models.create_c_serve_v2_deployment_response import CreateCServeV2DeploymentResponse -from platform_api_python_client.models.create_c_serve_v3_deployment_request import CreateCServeV3DeploymentRequest -from platform_api_python_client.models.create_c_serve_v3_deployment_response import CreateCServeV3DeploymentResponse from platform_api_python_client.models.create_compute_deployment_request import CreateComputeDeploymentRequest from platform_api_python_client.models.create_compute_deployment_response import CreateComputeDeploymentResponse from platform_api_python_client.models.create_dynamo_deployment_request import CreateDynamoDeploymentRequest @@ -66,6 +62,8 @@ from platform_api_python_client.models.dynamo_kv_transfer_configuration import DynamoKvTransferConfiguration from platform_api_python_client.models.dynamo_kv_transfer_policy import DynamoKvTransferPolicy from platform_api_python_client.models.dynamo_serving_mode import DynamoServingMode +from platform_api_python_client.models.dynamo_weight_transfer_configuration import DynamoWeightTransferConfiguration +from platform_api_python_client.models.dynamo_weight_transfer_policy import DynamoWeightTransferPolicy from platform_api_python_client.models.dynamo_worker_pool_config import DynamoWorkerPoolConfig from platform_api_python_client.models.dynamo_worker_pools import DynamoWorkerPools from platform_api_python_client.models.env import Env @@ -73,8 +71,6 @@ from platform_api_python_client.models.final_stack import FinalStack from platform_api_python_client.models.fluent_bit import FluentBit from platform_api_python_client.models.generate_service_account_secret_response import GenerateServiceAccountSecretResponse -from platform_api_python_client.models.get_c_serve_v2_deployment_response import GetCServeV2DeploymentResponse -from platform_api_python_client.models.get_c_serve_v3_deployment_response import GetCServeV3DeploymentResponse from platform_api_python_client.models.get_cluster_response import GetClusterResponse from platform_api_python_client.models.get_compute_deployment_response import GetComputeDeploymentResponse from platform_api_python_client.models.get_deployment_log_response import GetDeploymentLogResponse diff --git a/platform_api_python_client/models/c_serve_v2_recipe.py b/platform_api_python_client/models/c_serve_v2_recipe.py deleted file mode 100644 index 9dfbc48..0000000 --- a/platform_api_python_client/models/c_serve_v2_recipe.py +++ /dev/null @@ -1,109 +0,0 @@ -# coding: utf-8 - -""" - Platform External API - - No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) - - The version of the OpenAPI document: 0.1.0 - Generated by OpenAPI Generator (https://openapi-generator.tech) - - Do not edit the class manually. -""" # noqa: E501 - - -from __future__ import annotations -import pprint -import re # noqa: F401 -import json - -from pydantic import BaseModel, ConfigDict, StrictBool, StrictStr -from typing import Any, ClassVar, Dict, List, Optional -from typing import Optional, Set -from typing_extensions import Self - -class CServeV2Recipe(BaseModel): - """ - Inputs to start deployment - """ # noqa: E501 - model: StrictStr - revision: Optional[StrictStr] = None - is_embedding_model: Optional[StrictBool] = False - additional_properties: Dict[str, Any] = {} - __properties: ClassVar[List[str]] = ["model", "revision", "is_embedding_model"] - - model_config = ConfigDict( - populate_by_name=True, - validate_assignment=True, - protected_namespaces=(), - ) - - - def to_str(self) -> str: - """Returns the string representation of the model using alias""" - return pprint.pformat(self.model_dump(by_alias=True)) - - def to_json(self) -> str: - """Returns the JSON representation of the model using alias""" - # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead - return json.dumps(self.to_dict()) - - @classmethod - def from_json(cls, json_str: str) -> Optional[Self]: - """Create an instance of CServeV2Recipe from a JSON string""" - return cls.from_dict(json.loads(json_str)) - - def to_dict(self) -> Dict[str, Any]: - """Return the dictionary representation of the model using alias. - - This has the following differences from calling pydantic's - `self.model_dump(by_alias=True)`: - - * `None` is only added to the output dict for nullable fields that - were set at model initialization. Other fields with value `None` - are ignored. - * Fields in `self.additional_properties` are added to the output dict. - """ - excluded_fields: Set[str] = set([ - "additional_properties", - ]) - - _dict = self.model_dump( - by_alias=True, - exclude=excluded_fields, - exclude_none=True, - ) - # puts key-value pairs in additional_properties in the top level - if self.additional_properties is not None: - for _key, _value in self.additional_properties.items(): - _dict[_key] = _value - - # set to None if revision (nullable) is None - # and model_fields_set contains the field - if self.revision is None and "revision" in self.model_fields_set: - _dict['revision'] = None - - return _dict - - @classmethod - def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]: - """Create an instance of CServeV2Recipe from a dict""" - if obj is None: - return None - - if not isinstance(obj, dict): - return cls.model_validate(obj) - - _obj = cls.model_validate({ - "model": obj.get("model"), - "revision": obj.get("revision"), - "is_embedding_model": obj.get("is_embedding_model") if obj.get("is_embedding_model") is not None else False - }) - # store additional fields in additional_properties - for _key in obj.keys(): - if _key not in cls.__properties: - _obj.additional_properties[_key] = obj.get(_key) - - return _obj - - diff --git a/platform_api_python_client/models/create_c_serve_v3_deployment_request.py b/platform_api_python_client/models/create_c_serve_v3_deployment_request.py deleted file mode 100644 index 7745e06..0000000 --- a/platform_api_python_client/models/create_c_serve_v3_deployment_request.py +++ /dev/null @@ -1,215 +0,0 @@ -# coding: utf-8 - -""" - Platform External API - - No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) - - The version of the OpenAPI document: 0.1.0 - Generated by OpenAPI Generator (https://openapi-generator.tech) - - Do not edit the class manually. -""" # noqa: E501 - - -from __future__ import annotations -import pprint -import re # noqa: F401 -import json - -from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictInt, StrictStr, field_validator -from typing import Any, ClassVar, Dict, List, Optional -from typing_extensions import Annotated -from platform_api_python_client.models.c_serve_v2_recipe import CServeV2Recipe -from platform_api_python_client.models.volume_mount import VolumeMount -from typing import Optional, Set -from typing_extensions import Self - -class CreateCServeV3DeploymentRequest(BaseModel): - """ - CreateCServeV3DeploymentRequest - """ # noqa: E501 - max_surge: Optional[StrictInt] = None - max_unavailable: Optional[StrictInt] = None - name: Annotated[str, Field(min_length=1, strict=True, max_length=20)] - cluster_id: StrictInt - hardware_instance_id: StrictInt - user_annotations: Optional[Dict[str, StrictStr]] = None - chart_revision: Optional[StrictStr] = None - volume_mounts: Optional[Annotated[List[VolumeMount], Field(max_length=10)]] = None - priority: Optional[Annotated[str, Field(strict=True, max_length=253)]] = None - hf_token_ref: Optional[Annotated[int, Field(strict=True, ge=1)]] = None - recipe: CServeV2Recipe - cserve_version: Optional[StrictStr] = None - hf_token: Optional[StrictStr] = None - endpoint_bearer_token: Optional[StrictStr] = None - bearer_token_ref: Optional[Annotated[int, Field(strict=True, ge=1)]] = None - endpoint_certificate_authority: Optional[StrictStr] = None - min_replicas: StrictInt - max_replicas: StrictInt - concurrency: Optional[StrictInt] = None - cooldown_period: Optional[Annotated[int, Field(le=3600, strict=True, ge=0)]] = None - env_vars: Optional[Dict[str, StrictStr]] = None - env_vars_refs: Optional[Dict[str, Any]] = None - enable_logging: Optional[StrictBool] = True - enable_node_model_cache: Optional[StrictBool] = False - session_affinity: Optional[StrictBool] = Field(default=False, description="Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state.") - __properties: ClassVar[List[str]] = ["max_surge", "max_unavailable", "name", "cluster_id", "hardware_instance_id", "user_annotations", "chart_revision", "volume_mounts", "priority", "hf_token_ref", "recipe", "cserve_version", "hf_token", "endpoint_bearer_token", "bearer_token_ref", "endpoint_certificate_authority", "min_replicas", "max_replicas", "concurrency", "cooldown_period", "env_vars", "env_vars_refs", "enable_logging", "enable_node_model_cache", "session_affinity"] - - @field_validator('name') - def name_validate_regular_expression(cls, value): - """Validates the regular expression""" - if not re.match(r"^[a-z][a-z0-9-]*$", value): - raise ValueError(r"must validate the regular expression /^[a-z][a-z0-9-]*$/") - return value - - model_config = ConfigDict( - populate_by_name=True, - validate_assignment=True, - protected_namespaces=(), - ) - - - def to_str(self) -> str: - """Returns the string representation of the model using alias""" - return pprint.pformat(self.model_dump(by_alias=True)) - - def to_json(self) -> str: - """Returns the JSON representation of the model using alias""" - # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead - return json.dumps(self.to_dict()) - - @classmethod - def from_json(cls, json_str: str) -> Optional[Self]: - """Create an instance of CreateCServeV3DeploymentRequest from a JSON string""" - return cls.from_dict(json.loads(json_str)) - - def to_dict(self) -> Dict[str, Any]: - """Return the dictionary representation of the model using alias. - - This has the following differences from calling pydantic's - `self.model_dump(by_alias=True)`: - - * `None` is only added to the output dict for nullable fields that - were set at model initialization. Other fields with value `None` - are ignored. - """ - excluded_fields: Set[str] = set([ - ]) - - _dict = self.model_dump( - by_alias=True, - exclude=excluded_fields, - exclude_none=True, - ) - # override the default output from pydantic by calling `to_dict()` of each item in volume_mounts (list) - _items = [] - if self.volume_mounts: - for _item_volume_mounts in self.volume_mounts: - if _item_volume_mounts: - _items.append(_item_volume_mounts.to_dict()) - _dict['volume_mounts'] = _items - # override the default output from pydantic by calling `to_dict()` of recipe - if self.recipe: - _dict['recipe'] = self.recipe.to_dict() - # set to None if max_surge (nullable) is None - # and model_fields_set contains the field - if self.max_surge is None and "max_surge" in self.model_fields_set: - _dict['max_surge'] = None - - # set to None if max_unavailable (nullable) is None - # and model_fields_set contains the field - if self.max_unavailable is None and "max_unavailable" in self.model_fields_set: - _dict['max_unavailable'] = None - - # set to None if user_annotations (nullable) is None - # and model_fields_set contains the field - if self.user_annotations is None and "user_annotations" in self.model_fields_set: - _dict['user_annotations'] = None - - # set to None if priority (nullable) is None - # and model_fields_set contains the field - if self.priority is None and "priority" in self.model_fields_set: - _dict['priority'] = None - - # set to None if hf_token_ref (nullable) is None - # and model_fields_set contains the field - if self.hf_token_ref is None and "hf_token_ref" in self.model_fields_set: - _dict['hf_token_ref'] = None - - # set to None if cserve_version (nullable) is None - # and model_fields_set contains the field - if self.cserve_version is None and "cserve_version" in self.model_fields_set: - _dict['cserve_version'] = None - - # set to None if hf_token (nullable) is None - # and model_fields_set contains the field - if self.hf_token is None and "hf_token" in self.model_fields_set: - _dict['hf_token'] = None - - # set to None if endpoint_bearer_token (nullable) is None - # and model_fields_set contains the field - if self.endpoint_bearer_token is None and "endpoint_bearer_token" in self.model_fields_set: - _dict['endpoint_bearer_token'] = None - - # set to None if bearer_token_ref (nullable) is None - # and model_fields_set contains the field - if self.bearer_token_ref is None and "bearer_token_ref" in self.model_fields_set: - _dict['bearer_token_ref'] = None - - # set to None if endpoint_certificate_authority (nullable) is None - # and model_fields_set contains the field - if self.endpoint_certificate_authority is None and "endpoint_certificate_authority" in self.model_fields_set: - _dict['endpoint_certificate_authority'] = None - - # set to None if concurrency (nullable) is None - # and model_fields_set contains the field - if self.concurrency is None and "concurrency" in self.model_fields_set: - _dict['concurrency'] = None - - # set to None if cooldown_period (nullable) is None - # and model_fields_set contains the field - if self.cooldown_period is None and "cooldown_period" in self.model_fields_set: - _dict['cooldown_period'] = None - - return _dict - - @classmethod - def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]: - """Create an instance of CreateCServeV3DeploymentRequest from a dict""" - if obj is None: - return None - - if not isinstance(obj, dict): - return cls.model_validate(obj) - - _obj = cls.model_validate({ - "max_surge": obj.get("max_surge"), - "max_unavailable": obj.get("max_unavailable"), - "name": obj.get("name"), - "cluster_id": obj.get("cluster_id"), - "hardware_instance_id": obj.get("hardware_instance_id"), - "user_annotations": obj.get("user_annotations"), - "chart_revision": obj.get("chart_revision"), - "volume_mounts": [VolumeMount.from_dict(_item) for _item in obj["volume_mounts"]] if obj.get("volume_mounts") is not None else None, - "priority": obj.get("priority"), - "hf_token_ref": obj.get("hf_token_ref"), - "recipe": CServeV2Recipe.from_dict(obj["recipe"]) if obj.get("recipe") is not None else None, - "cserve_version": obj.get("cserve_version"), - "hf_token": obj.get("hf_token"), - "endpoint_bearer_token": obj.get("endpoint_bearer_token"), - "bearer_token_ref": obj.get("bearer_token_ref"), - "endpoint_certificate_authority": obj.get("endpoint_certificate_authority"), - "min_replicas": obj.get("min_replicas"), - "max_replicas": obj.get("max_replicas"), - "concurrency": obj.get("concurrency"), - "cooldown_period": obj.get("cooldown_period"), - "env_vars": obj.get("env_vars"), - "env_vars_refs": obj.get("env_vars_refs"), - "enable_logging": obj.get("enable_logging") if obj.get("enable_logging") is not None else True, - "enable_node_model_cache": obj.get("enable_node_model_cache") if obj.get("enable_node_model_cache") is not None else False, - "session_affinity": obj.get("session_affinity") if obj.get("session_affinity") is not None else False - }) - return _obj - - diff --git a/platform_api_python_client/models/create_c_serve_v3_deployment_response.py b/platform_api_python_client/models/create_c_serve_v3_deployment_response.py deleted file mode 100644 index 816bb9b..0000000 --- a/platform_api_python_client/models/create_c_serve_v3_deployment_response.py +++ /dev/null @@ -1,92 +0,0 @@ -# coding: utf-8 - -""" - Platform External API - - No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) - - The version of the OpenAPI document: 0.1.0 - Generated by OpenAPI Generator (https://openapi-generator.tech) - - Do not edit the class manually. -""" # noqa: E501 - - -from __future__ import annotations -import pprint -import re # noqa: F401 -import json - -from datetime import datetime -from pydantic import BaseModel, ConfigDict, StrictInt, StrictStr -from typing import Any, ClassVar, Dict, List -from typing import Optional, Set -from typing_extensions import Self - -class CreateCServeV3DeploymentResponse(BaseModel): - """ - CreateCServeV3DeploymentResponse - """ # noqa: E501 - id: StrictInt - created_at: datetime - endpoint_url: StrictStr - __properties: ClassVar[List[str]] = ["id", "created_at", "endpoint_url"] - - model_config = ConfigDict( - populate_by_name=True, - validate_assignment=True, - protected_namespaces=(), - ) - - - def to_str(self) -> str: - """Returns the string representation of the model using alias""" - return pprint.pformat(self.model_dump(by_alias=True)) - - def to_json(self) -> str: - """Returns the JSON representation of the model using alias""" - # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead - return json.dumps(self.to_dict()) - - @classmethod - def from_json(cls, json_str: str) -> Optional[Self]: - """Create an instance of CreateCServeV3DeploymentResponse from a JSON string""" - return cls.from_dict(json.loads(json_str)) - - def to_dict(self) -> Dict[str, Any]: - """Return the dictionary representation of the model using alias. - - This has the following differences from calling pydantic's - `self.model_dump(by_alias=True)`: - - * `None` is only added to the output dict for nullable fields that - were set at model initialization. Other fields with value `None` - are ignored. - """ - excluded_fields: Set[str] = set([ - ]) - - _dict = self.model_dump( - by_alias=True, - exclude=excluded_fields, - exclude_none=True, - ) - return _dict - - @classmethod - def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]: - """Create an instance of CreateCServeV3DeploymentResponse from a dict""" - if obj is None: - return None - - if not isinstance(obj, dict): - return cls.model_validate(obj) - - _obj = cls.model_validate({ - "id": obj.get("id"), - "created_at": obj.get("created_at"), - "endpoint_url": obj.get("endpoint_url") - }) - return _obj - - diff --git a/platform_api_python_client/models/create_dynamo_deployment_request.py b/platform_api_python_client/models/create_dynamo_deployment_request.py index e78d133..7ca52d1 100644 --- a/platform_api_python_client/models/create_dynamo_deployment_request.py +++ b/platform_api_python_client/models/create_dynamo_deployment_request.py @@ -23,6 +23,7 @@ from platform_api_python_client.models.backend_protocol import BackendProtocol from platform_api_python_client.models.dynamo_communications_input import DynamoCommunicationsInput from platform_api_python_client.models.dynamo_serving_mode import DynamoServingMode +from platform_api_python_client.models.dynamo_weight_transfer_configuration import DynamoWeightTransferConfiguration from platform_api_python_client.models.dynamo_worker_pools import DynamoWorkerPools from platform_api_python_client.models.volume_mount import VolumeMount from typing import Optional, Set @@ -44,7 +45,9 @@ class CreateDynamoDeploymentRequest(BaseModel): serving_mode: Optional[DynamoServingMode] = None worker_pools: Optional[DynamoWorkerPools] = None communications: Optional[DynamoCommunicationsInput] = None + weight_transfer: Optional[DynamoWeightTransferConfiguration] = None model: StrictStr + model_revision: Optional[Annotated[str, Field(min_length=1, strict=True)]] = None served_model_name: Optional[StrictStr] = None runtime_version: Optional[Annotated[str, Field(strict=True)]] = Field(default=None, description="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. require_gpu_direct_rdma needs an EFA-capable image. Changing it restarts every component of a running deployment.") min_replicas: Optional[StrictInt] = None @@ -63,7 +66,7 @@ class CreateDynamoDeploymentRequest(BaseModel): enable_logging: Optional[StrictBool] = True enable_node_model_cache: Optional[StrictBool] = False backend_protocol: Optional[BackendProtocol] = None - __properties: ClassVar[List[str]] = ["max_surge", "max_unavailable", "name", "cluster_id", "hardware_instance_id", "user_annotations", "chart_revision", "volume_mounts", "priority", "serving_mode", "worker_pools", "communications", "model", "served_model_name", "runtime_version", "min_replicas", "max_replicas", "concurrency", "cooldown_period", "extra_args", "hf_token", "hf_token_ref", "env_vars", "env_vars_refs", "endpoint_bearer_token", "bearer_token_ref", "endpoint_certificate_authority", "image_pull_ref", "enable_logging", "enable_node_model_cache", "backend_protocol"] + __properties: ClassVar[List[str]] = ["max_surge", "max_unavailable", "name", "cluster_id", "hardware_instance_id", "user_annotations", "chart_revision", "volume_mounts", "priority", "serving_mode", "worker_pools", "communications", "weight_transfer", "model", "model_revision", "served_model_name", "runtime_version", "min_replicas", "max_replicas", "concurrency", "cooldown_period", "extra_args", "hf_token", "hf_token_ref", "env_vars", "env_vars_refs", "endpoint_bearer_token", "bearer_token_ref", "endpoint_certificate_authority", "image_pull_ref", "enable_logging", "enable_node_model_cache", "backend_protocol"] @field_validator('name') def name_validate_regular_expression(cls, value): @@ -134,6 +137,9 @@ def to_dict(self) -> Dict[str, Any]: # override the default output from pydantic by calling `to_dict()` of communications if self.communications: _dict['communications'] = self.communications.to_dict() + # override the default output from pydantic by calling `to_dict()` of weight_transfer + if self.weight_transfer: + _dict['weight_transfer'] = self.weight_transfer.to_dict() # set to None if max_surge (nullable) is None # and model_fields_set contains the field if self.max_surge is None and "max_surge" in self.model_fields_set: @@ -169,6 +175,16 @@ def to_dict(self) -> Dict[str, Any]: if self.communications is None and "communications" in self.model_fields_set: _dict['communications'] = None + # set to None if weight_transfer (nullable) is None + # and model_fields_set contains the field + if self.weight_transfer is None and "weight_transfer" in self.model_fields_set: + _dict['weight_transfer'] = None + + # set to None if model_revision (nullable) is None + # and model_fields_set contains the field + if self.model_revision is None and "model_revision" in self.model_fields_set: + _dict['model_revision'] = None + # set to None if served_model_name (nullable) is None # and model_fields_set contains the field if self.served_model_name is None and "served_model_name" in self.model_fields_set: @@ -253,7 +269,9 @@ def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]: "serving_mode": obj.get("serving_mode"), "worker_pools": DynamoWorkerPools.from_dict(obj["worker_pools"]) if obj.get("worker_pools") is not None else None, "communications": DynamoCommunicationsInput.from_dict(obj["communications"]) if obj.get("communications") is not None else None, + "weight_transfer": DynamoWeightTransferConfiguration.from_dict(obj["weight_transfer"]) if obj.get("weight_transfer") is not None else None, "model": obj.get("model"), + "model_revision": obj.get("model_revision"), "served_model_name": obj.get("served_model_name"), "runtime_version": obj.get("runtime_version"), "min_replicas": obj.get("min_replicas"), diff --git a/platform_api_python_client/models/deployment_response.py b/platform_api_python_client/models/deployment_response.py index 947f897..6aa5731 100644 --- a/platform_api_python_client/models/deployment_response.py +++ b/platform_api_python_client/models/deployment_response.py @@ -19,7 +19,6 @@ import re # noqa: F401 from pydantic import BaseModel, ConfigDict, Field, StrictStr, ValidationError, field_validator from typing import Optional -from platform_api_python_client.models.get_c_serve_v3_deployment_response import GetCServeV3DeploymentResponse from platform_api_python_client.models.get_compute_deployment_response import GetComputeDeploymentResponse from platform_api_python_client.models.get_dynamo_deployment_response import GetDynamoDeploymentResponse from platform_api_python_client.models.get_inference_v3_deployment_response import GetInferenceV3DeploymentResponse @@ -28,7 +27,7 @@ from typing_extensions import Literal, Self from pydantic import Field -DEPLOYMENTRESPONSE_ANY_OF_SCHEMAS = ["GetCServeV3DeploymentResponse", "GetComputeDeploymentResponse", "GetDynamoDeploymentResponse", "GetInferenceV3DeploymentResponse", "GetJobDeploymentResponse"] +DEPLOYMENTRESPONSE_ANY_OF_SCHEMAS = ["GetComputeDeploymentResponse", "GetDynamoDeploymentResponse", "GetInferenceV3DeploymentResponse", "GetJobDeploymentResponse"] class DeploymentResponse(BaseModel): """ @@ -37,19 +36,17 @@ class DeploymentResponse(BaseModel): # data type: GetDynamoDeploymentResponse anyof_schema_1_validator: Optional[GetDynamoDeploymentResponse] = None - # data type: GetCServeV3DeploymentResponse - anyof_schema_2_validator: Optional[GetCServeV3DeploymentResponse] = None # data type: GetInferenceV3DeploymentResponse - anyof_schema_3_validator: Optional[GetInferenceV3DeploymentResponse] = None + anyof_schema_2_validator: Optional[GetInferenceV3DeploymentResponse] = None # data type: GetComputeDeploymentResponse - anyof_schema_4_validator: Optional[GetComputeDeploymentResponse] = None + anyof_schema_3_validator: Optional[GetComputeDeploymentResponse] = None # data type: GetJobDeploymentResponse - anyof_schema_5_validator: Optional[GetJobDeploymentResponse] = None + anyof_schema_4_validator: Optional[GetJobDeploymentResponse] = None if TYPE_CHECKING: - actual_instance: Optional[Union[GetCServeV3DeploymentResponse, GetComputeDeploymentResponse, GetDynamoDeploymentResponse, GetInferenceV3DeploymentResponse, GetJobDeploymentResponse]] = None + actual_instance: Optional[Union[GetComputeDeploymentResponse, GetDynamoDeploymentResponse, GetInferenceV3DeploymentResponse, GetJobDeploymentResponse]] = None else: actual_instance: Any = None - any_of_schemas: Set[str] = { "GetCServeV3DeploymentResponse", "GetComputeDeploymentResponse", "GetDynamoDeploymentResponse", "GetInferenceV3DeploymentResponse", "GetJobDeploymentResponse" } + any_of_schemas: Set[str] = { "GetComputeDeploymentResponse", "GetDynamoDeploymentResponse", "GetInferenceV3DeploymentResponse", "GetJobDeploymentResponse" } model_config = { "validate_assignment": True, @@ -76,12 +73,6 @@ def actual_instance_must_validate_anyof(cls, v): else: return v - # validate data type: GetCServeV3DeploymentResponse - if not isinstance(v, GetCServeV3DeploymentResponse): - error_messages.append(f"Error! Input type `{type(v)}` is not `GetCServeV3DeploymentResponse`") - else: - return v - # validate data type: GetInferenceV3DeploymentResponse if not isinstance(v, GetInferenceV3DeploymentResponse): error_messages.append(f"Error! Input type `{type(v)}` is not `GetInferenceV3DeploymentResponse`") @@ -102,7 +93,7 @@ def actual_instance_must_validate_anyof(cls, v): if error_messages: # no match - raise ValueError("No match found when setting the actual_instance in DeploymentResponse with anyOf schemas: GetCServeV3DeploymentResponse, GetComputeDeploymentResponse, GetDynamoDeploymentResponse, GetInferenceV3DeploymentResponse, GetJobDeploymentResponse. Details: " + ", ".join(error_messages)) + raise ValueError("No match found when setting the actual_instance in DeploymentResponse with anyOf schemas: GetComputeDeploymentResponse, GetDynamoDeploymentResponse, GetInferenceV3DeploymentResponse, GetJobDeploymentResponse. Details: " + ", ".join(error_messages)) else: return v @@ -121,25 +112,19 @@ def from_json(cls, json_str: str) -> Self: return instance except (ValidationError, ValueError) as e: error_messages.append(str(e)) - # anyof_schema_2_validator: Optional[GetCServeV3DeploymentResponse] = None - try: - instance.actual_instance = GetCServeV3DeploymentResponse.from_json(json_str) - return instance - except (ValidationError, ValueError) as e: - error_messages.append(str(e)) - # anyof_schema_3_validator: Optional[GetInferenceV3DeploymentResponse] = None + # anyof_schema_2_validator: Optional[GetInferenceV3DeploymentResponse] = None try: instance.actual_instance = GetInferenceV3DeploymentResponse.from_json(json_str) return instance except (ValidationError, ValueError) as e: error_messages.append(str(e)) - # anyof_schema_4_validator: Optional[GetComputeDeploymentResponse] = None + # anyof_schema_3_validator: Optional[GetComputeDeploymentResponse] = None try: instance.actual_instance = GetComputeDeploymentResponse.from_json(json_str) return instance except (ValidationError, ValueError) as e: error_messages.append(str(e)) - # anyof_schema_5_validator: Optional[GetJobDeploymentResponse] = None + # anyof_schema_4_validator: Optional[GetJobDeploymentResponse] = None try: instance.actual_instance = GetJobDeploymentResponse.from_json(json_str) return instance @@ -148,7 +133,7 @@ def from_json(cls, json_str: str) -> Self: if error_messages: # no match - raise ValueError("No match found when deserializing the JSON string into DeploymentResponse with anyOf schemas: GetCServeV3DeploymentResponse, GetComputeDeploymentResponse, GetDynamoDeploymentResponse, GetInferenceV3DeploymentResponse, GetJobDeploymentResponse. Details: " + ", ".join(error_messages)) + raise ValueError("No match found when deserializing the JSON string into DeploymentResponse with anyOf schemas: GetComputeDeploymentResponse, GetDynamoDeploymentResponse, GetInferenceV3DeploymentResponse, GetJobDeploymentResponse. Details: " + ", ".join(error_messages)) else: return instance @@ -162,7 +147,7 @@ def to_json(self) -> str: else: return json.dumps(self.actual_instance) - def to_dict(self) -> Optional[Union[Dict[str, Any], GetCServeV3DeploymentResponse, GetComputeDeploymentResponse, GetDynamoDeploymentResponse, GetInferenceV3DeploymentResponse, GetJobDeploymentResponse]]: + def to_dict(self) -> Optional[Union[Dict[str, Any], GetComputeDeploymentResponse, GetDynamoDeploymentResponse, GetInferenceV3DeploymentResponse, GetJobDeploymentResponse]]: """Returns the dict representation of the actual instance""" if self.actual_instance is None: return None diff --git a/platform_api_python_client/models/create_c_serve_v2_deployment_response.py b/platform_api_python_client/models/dynamo_weight_transfer_configuration.py similarity index 62% rename from platform_api_python_client/models/create_c_serve_v2_deployment_response.py rename to platform_api_python_client/models/dynamo_weight_transfer_configuration.py index 46b471b..8d41f2c 100644 --- a/platform_api_python_client/models/create_c_serve_v2_deployment_response.py +++ b/platform_api_python_client/models/dynamo_weight_transfer_configuration.py @@ -17,20 +17,18 @@ import re # noqa: F401 import json -from datetime import datetime -from pydantic import BaseModel, ConfigDict, StrictInt, StrictStr -from typing import Any, ClassVar, Dict, List +from pydantic import BaseModel, ConfigDict, Field +from typing import Any, ClassVar, Dict, List, Optional +from platform_api_python_client.models.dynamo_weight_transfer_policy import DynamoWeightTransferPolicy from typing import Optional, Set from typing_extensions import Self -class CreateCServeV2DeploymentResponse(BaseModel): +class DynamoWeightTransferConfiguration(BaseModel): """ - CreateCServeV2DeploymentResponse + ModelExpress peer weight transfer between the workers of one pool, in either serving mode. """ # noqa: E501 - id: StrictInt - created_at: datetime - endpoint_url: StrictStr - __properties: ClassVar[List[str]] = ["id", "created_at", "endpoint_url"] + policy: Optional[DynamoWeightTransferPolicy] = Field(default=None, description="The default and only policy, so an empty object opts in. require_gpu_direct_rdma makes a starting worker pull the model's weights GPU to GPU from a worker of the same pool that already serves the same model_revision commit, over the cluster's GPU-direct RDMA fabric (currently AWS EFA only), instead of downloading the checkpoint. A pool's first worker, or one without a reachable peer, falls back to the usual loader. The chart and runtime image prerequisites of require_gpu_direct_rdma KV transfer apply; the API does not validate them.") + __properties: ClassVar[List[str]] = ["policy"] model_config = ConfigDict( populate_by_name=True, @@ -50,7 +48,7 @@ def to_json(self) -> str: @classmethod def from_json(cls, json_str: str) -> Optional[Self]: - """Create an instance of CreateCServeV2DeploymentResponse from a JSON string""" + """Create an instance of DynamoWeightTransferConfiguration from a JSON string""" return cls.from_dict(json.loads(json_str)) def to_dict(self) -> Dict[str, Any]: @@ -75,7 +73,7 @@ def to_dict(self) -> Dict[str, Any]: @classmethod def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]: - """Create an instance of CreateCServeV2DeploymentResponse from a dict""" + """Create an instance of DynamoWeightTransferConfiguration from a dict""" if obj is None: return None @@ -83,9 +81,7 @@ def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]: return cls.model_validate(obj) _obj = cls.model_validate({ - "id": obj.get("id"), - "created_at": obj.get("created_at"), - "endpoint_url": obj.get("endpoint_url") + "policy": obj.get("policy") }) return _obj diff --git a/platform_api_python_client/models/dynamo_weight_transfer_policy.py b/platform_api_python_client/models/dynamo_weight_transfer_policy.py new file mode 100644 index 0000000..261bd97 --- /dev/null +++ b/platform_api_python_client/models/dynamo_weight_transfer_policy.py @@ -0,0 +1,36 @@ +# coding: utf-8 + +""" + Platform External API + + No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) + + The version of the OpenAPI document: 0.1.0 + Generated by OpenAPI Generator (https://openapi-generator.tech) + + Do not edit the class manually. +""" # noqa: E501 + + +from __future__ import annotations +import json +from enum import Enum +from typing_extensions import Self + + +class DynamoWeightTransferPolicy(str, Enum): + """ + DynamoWeightTransferPolicy + """ + + """ + allowed enum values + """ + REQUIRE_GPU_DIRECT_RDMA = 'require_gpu_direct_rdma' + + @classmethod + def from_json(cls, json_str: str) -> Self: + """Create an instance of DynamoWeightTransferPolicy from a JSON string""" + return cls(json.loads(json_str)) + + diff --git a/platform_api_python_client/models/get_c_serve_v2_deployment_response.py b/platform_api_python_client/models/get_c_serve_v2_deployment_response.py deleted file mode 100644 index c4bcba6..0000000 --- a/platform_api_python_client/models/get_c_serve_v2_deployment_response.py +++ /dev/null @@ -1,193 +0,0 @@ -# coding: utf-8 - -""" - Platform External API - - No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) - - The version of the OpenAPI document: 0.1.0 - Generated by OpenAPI Generator (https://openapi-generator.tech) - - Do not edit the class manually. -""" # noqa: E501 - - -from __future__ import annotations -import pprint -import re # noqa: F401 -import json - -from datetime import datetime -from pydantic import BaseModel, ConfigDict, StrictInt, StrictStr -from typing import Any, ClassVar, Dict, List, Optional -from platform_api_python_client.models.c_serve_v2_recipe import CServeV2Recipe -from platform_api_python_client.models.deployment_status import DeploymentStatus -from platform_api_python_client.models.deployment_type import DeploymentType -from platform_api_python_client.models.volume_mount import VolumeMount -from typing import Optional, Set -from typing_extensions import Self - -class GetCServeV2DeploymentResponse(BaseModel): - """ - GetCServeV2DeploymentResponse - """ # noqa: E501 - creator_email: StrictStr - cluster_id: StrictInt - id: StrictInt - name: StrictStr - endpoint_url: StrictStr - image_url: Optional[StrictStr] = None - type: DeploymentType - status: DeploymentStatus - created_at: datetime - hardware_instance_id: StrictInt - revision_number: StrictInt - chart_revision: Optional[StrictStr] = None - user_annotations: Optional[Dict[str, StrictStr]] = None - priority: Optional[StrictStr] = None - volume_mounts: Optional[List[VolumeMount]] = None - recipe: CServeV2Recipe - cserve_version: Optional[StrictStr] = None - min_scale: StrictInt - max_scale: StrictInt - initial_scale: Optional[StrictInt] = None - endpoint_certificate_authority: Optional[StrictStr] = None - endpoint_bearer_token: Optional[StrictStr] = None - concurrency: Optional[StrictInt] = None - env_vars: Optional[Dict[str, StrictStr]] = None - __properties: ClassVar[List[str]] = ["creator_email", "cluster_id", "id", "name", "endpoint_url", "image_url", "type", "status", "created_at", "hardware_instance_id", "revision_number", "chart_revision", "user_annotations", "priority", "volume_mounts", "recipe", "cserve_version", "min_scale", "max_scale", "initial_scale", "endpoint_certificate_authority", "endpoint_bearer_token", "concurrency", "env_vars"] - - model_config = ConfigDict( - populate_by_name=True, - validate_assignment=True, - protected_namespaces=(), - ) - - - def to_str(self) -> str: - """Returns the string representation of the model using alias""" - return pprint.pformat(self.model_dump(by_alias=True)) - - def to_json(self) -> str: - """Returns the JSON representation of the model using alias""" - # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead - return json.dumps(self.to_dict()) - - @classmethod - def from_json(cls, json_str: str) -> Optional[Self]: - """Create an instance of GetCServeV2DeploymentResponse from a JSON string""" - return cls.from_dict(json.loads(json_str)) - - def to_dict(self) -> Dict[str, Any]: - """Return the dictionary representation of the model using alias. - - This has the following differences from calling pydantic's - `self.model_dump(by_alias=True)`: - - * `None` is only added to the output dict for nullable fields that - were set at model initialization. Other fields with value `None` - are ignored. - """ - excluded_fields: Set[str] = set([ - ]) - - _dict = self.model_dump( - by_alias=True, - exclude=excluded_fields, - exclude_none=True, - ) - # override the default output from pydantic by calling `to_dict()` of each item in volume_mounts (list) - _items = [] - if self.volume_mounts: - for _item_volume_mounts in self.volume_mounts: - if _item_volume_mounts: - _items.append(_item_volume_mounts.to_dict()) - _dict['volume_mounts'] = _items - # override the default output from pydantic by calling `to_dict()` of recipe - if self.recipe: - _dict['recipe'] = self.recipe.to_dict() - # set to None if image_url (nullable) is None - # and model_fields_set contains the field - if self.image_url is None and "image_url" in self.model_fields_set: - _dict['image_url'] = None - - # set to None if chart_revision (nullable) is None - # and model_fields_set contains the field - if self.chart_revision is None and "chart_revision" in self.model_fields_set: - _dict['chart_revision'] = None - - # set to None if user_annotations (nullable) is None - # and model_fields_set contains the field - if self.user_annotations is None and "user_annotations" in self.model_fields_set: - _dict['user_annotations'] = None - - # set to None if priority (nullable) is None - # and model_fields_set contains the field - if self.priority is None and "priority" in self.model_fields_set: - _dict['priority'] = None - - # set to None if cserve_version (nullable) is None - # and model_fields_set contains the field - if self.cserve_version is None and "cserve_version" in self.model_fields_set: - _dict['cserve_version'] = None - - # set to None if initial_scale (nullable) is None - # and model_fields_set contains the field - if self.initial_scale is None and "initial_scale" in self.model_fields_set: - _dict['initial_scale'] = None - - # set to None if endpoint_certificate_authority (nullable) is None - # and model_fields_set contains the field - if self.endpoint_certificate_authority is None and "endpoint_certificate_authority" in self.model_fields_set: - _dict['endpoint_certificate_authority'] = None - - # set to None if endpoint_bearer_token (nullable) is None - # and model_fields_set contains the field - if self.endpoint_bearer_token is None and "endpoint_bearer_token" in self.model_fields_set: - _dict['endpoint_bearer_token'] = None - - # set to None if concurrency (nullable) is None - # and model_fields_set contains the field - if self.concurrency is None and "concurrency" in self.model_fields_set: - _dict['concurrency'] = None - - return _dict - - @classmethod - def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]: - """Create an instance of GetCServeV2DeploymentResponse from a dict""" - if obj is None: - return None - - if not isinstance(obj, dict): - return cls.model_validate(obj) - - _obj = cls.model_validate({ - "creator_email": obj.get("creator_email"), - "cluster_id": obj.get("cluster_id"), - "id": obj.get("id"), - "name": obj.get("name"), - "endpoint_url": obj.get("endpoint_url"), - "image_url": obj.get("image_url"), - "type": obj.get("type"), - "status": obj.get("status"), - "created_at": obj.get("created_at"), - "hardware_instance_id": obj.get("hardware_instance_id"), - "revision_number": obj.get("revision_number"), - "chart_revision": obj.get("chart_revision"), - "user_annotations": obj.get("user_annotations"), - "priority": obj.get("priority"), - "volume_mounts": [VolumeMount.from_dict(_item) for _item in obj["volume_mounts"]] if obj.get("volume_mounts") is not None else None, - "recipe": CServeV2Recipe.from_dict(obj["recipe"]) if obj.get("recipe") is not None else None, - "cserve_version": obj.get("cserve_version"), - "min_scale": obj.get("min_scale"), - "max_scale": obj.get("max_scale"), - "initial_scale": obj.get("initial_scale"), - "endpoint_certificate_authority": obj.get("endpoint_certificate_authority"), - "endpoint_bearer_token": obj.get("endpoint_bearer_token"), - "concurrency": obj.get("concurrency"), - "env_vars": obj.get("env_vars") - }) - return _obj - - diff --git a/platform_api_python_client/models/get_c_serve_v3_deployment_response.py b/platform_api_python_client/models/get_c_serve_v3_deployment_response.py deleted file mode 100644 index 287a1a4..0000000 --- a/platform_api_python_client/models/get_c_serve_v3_deployment_response.py +++ /dev/null @@ -1,211 +0,0 @@ -# coding: utf-8 - -""" - Platform External API - - No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) - - The version of the OpenAPI document: 0.1.0 - Generated by OpenAPI Generator (https://openapi-generator.tech) - - Do not edit the class manually. -""" # noqa: E501 - - -from __future__ import annotations -import pprint -import re # noqa: F401 -import json - -from datetime import datetime -from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictInt, StrictStr -from typing import Any, ClassVar, Dict, List, Optional -from typing_extensions import Annotated -from platform_api_python_client.models.c_serve_v2_recipe import CServeV2Recipe -from platform_api_python_client.models.deployment_status import DeploymentStatus -from platform_api_python_client.models.deployment_type import DeploymentType -from platform_api_python_client.models.volume_mount import VolumeMount -from typing import Optional, Set -from typing_extensions import Self - -class GetCServeV3DeploymentResponse(BaseModel): - """ - GetCServeV3DeploymentResponse - """ # noqa: E501 - creator_email: StrictStr - cluster_id: StrictInt - id: StrictInt - name: StrictStr - endpoint_url: StrictStr - image_url: Optional[StrictStr] = None - type: DeploymentType - status: DeploymentStatus - created_at: datetime - hardware_instance_id: StrictInt - revision_number: StrictInt - chart_revision: Optional[StrictStr] = None - user_annotations: Optional[Dict[str, StrictStr]] = None - priority: Optional[StrictStr] = None - volume_mounts: Optional[List[VolumeMount]] = None - hf_token_ref: Optional[Annotated[int, Field(strict=True, ge=1)]] = None - recipe: CServeV2Recipe - cserve_version: Optional[StrictStr] = None - min_replicas: StrictInt - max_replicas: StrictInt - endpoint_certificate_authority: Optional[StrictStr] = None - endpoint_bearer_token: Optional[StrictStr] = None - concurrency: Optional[StrictInt] = None - cooldown_period: Optional[StrictInt] = 1800 - env_vars: Optional[Dict[str, StrictStr]] = None - env_vars_refs: Optional[Dict[str, Any]] = None - bearer_token_ref: Optional[Annotated[int, Field(strict=True, ge=1)]] = None - enable_logging: Optional[StrictBool] = True - enable_node_model_cache: Optional[StrictBool] = False - session_affinity: Optional[StrictBool] = Field(default=False, description="Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state.") - __properties: ClassVar[List[str]] = ["creator_email", "cluster_id", "id", "name", "endpoint_url", "image_url", "type", "status", "created_at", "hardware_instance_id", "revision_number", "chart_revision", "user_annotations", "priority", "volume_mounts", "hf_token_ref", "recipe", "cserve_version", "min_replicas", "max_replicas", "endpoint_certificate_authority", "endpoint_bearer_token", "concurrency", "cooldown_period", "env_vars", "env_vars_refs", "bearer_token_ref", "enable_logging", "enable_node_model_cache", "session_affinity"] - - model_config = ConfigDict( - populate_by_name=True, - validate_assignment=True, - protected_namespaces=(), - ) - - - def to_str(self) -> str: - """Returns the string representation of the model using alias""" - return pprint.pformat(self.model_dump(by_alias=True)) - - def to_json(self) -> str: - """Returns the JSON representation of the model using alias""" - # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead - return json.dumps(self.to_dict()) - - @classmethod - def from_json(cls, json_str: str) -> Optional[Self]: - """Create an instance of GetCServeV3DeploymentResponse from a JSON string""" - return cls.from_dict(json.loads(json_str)) - - def to_dict(self) -> Dict[str, Any]: - """Return the dictionary representation of the model using alias. - - This has the following differences from calling pydantic's - `self.model_dump(by_alias=True)`: - - * `None` is only added to the output dict for nullable fields that - were set at model initialization. Other fields with value `None` - are ignored. - """ - excluded_fields: Set[str] = set([ - ]) - - _dict = self.model_dump( - by_alias=True, - exclude=excluded_fields, - exclude_none=True, - ) - # override the default output from pydantic by calling `to_dict()` of each item in volume_mounts (list) - _items = [] - if self.volume_mounts: - for _item_volume_mounts in self.volume_mounts: - if _item_volume_mounts: - _items.append(_item_volume_mounts.to_dict()) - _dict['volume_mounts'] = _items - # override the default output from pydantic by calling `to_dict()` of recipe - if self.recipe: - _dict['recipe'] = self.recipe.to_dict() - # set to None if image_url (nullable) is None - # and model_fields_set contains the field - if self.image_url is None and "image_url" in self.model_fields_set: - _dict['image_url'] = None - - # set to None if chart_revision (nullable) is None - # and model_fields_set contains the field - if self.chart_revision is None and "chart_revision" in self.model_fields_set: - _dict['chart_revision'] = None - - # set to None if user_annotations (nullable) is None - # and model_fields_set contains the field - if self.user_annotations is None and "user_annotations" in self.model_fields_set: - _dict['user_annotations'] = None - - # set to None if priority (nullable) is None - # and model_fields_set contains the field - if self.priority is None and "priority" in self.model_fields_set: - _dict['priority'] = None - - # set to None if hf_token_ref (nullable) is None - # and model_fields_set contains the field - if self.hf_token_ref is None and "hf_token_ref" in self.model_fields_set: - _dict['hf_token_ref'] = None - - # set to None if cserve_version (nullable) is None - # and model_fields_set contains the field - if self.cserve_version is None and "cserve_version" in self.model_fields_set: - _dict['cserve_version'] = None - - # set to None if endpoint_certificate_authority (nullable) is None - # and model_fields_set contains the field - if self.endpoint_certificate_authority is None and "endpoint_certificate_authority" in self.model_fields_set: - _dict['endpoint_certificate_authority'] = None - - # set to None if endpoint_bearer_token (nullable) is None - # and model_fields_set contains the field - if self.endpoint_bearer_token is None and "endpoint_bearer_token" in self.model_fields_set: - _dict['endpoint_bearer_token'] = None - - # set to None if concurrency (nullable) is None - # and model_fields_set contains the field - if self.concurrency is None and "concurrency" in self.model_fields_set: - _dict['concurrency'] = None - - # set to None if bearer_token_ref (nullable) is None - # and model_fields_set contains the field - if self.bearer_token_ref is None and "bearer_token_ref" in self.model_fields_set: - _dict['bearer_token_ref'] = None - - return _dict - - @classmethod - def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]: - """Create an instance of GetCServeV3DeploymentResponse from a dict""" - if obj is None: - return None - - if not isinstance(obj, dict): - return cls.model_validate(obj) - - _obj = cls.model_validate({ - "creator_email": obj.get("creator_email"), - "cluster_id": obj.get("cluster_id"), - "id": obj.get("id"), - "name": obj.get("name"), - "endpoint_url": obj.get("endpoint_url"), - "image_url": obj.get("image_url"), - "type": obj.get("type"), - "status": obj.get("status"), - "created_at": obj.get("created_at"), - "hardware_instance_id": obj.get("hardware_instance_id"), - "revision_number": obj.get("revision_number"), - "chart_revision": obj.get("chart_revision"), - "user_annotations": obj.get("user_annotations"), - "priority": obj.get("priority"), - "volume_mounts": [VolumeMount.from_dict(_item) for _item in obj["volume_mounts"]] if obj.get("volume_mounts") is not None else None, - "hf_token_ref": obj.get("hf_token_ref"), - "recipe": CServeV2Recipe.from_dict(obj["recipe"]) if obj.get("recipe") is not None else None, - "cserve_version": obj.get("cserve_version"), - "min_replicas": obj.get("min_replicas"), - "max_replicas": obj.get("max_replicas"), - "endpoint_certificate_authority": obj.get("endpoint_certificate_authority"), - "endpoint_bearer_token": obj.get("endpoint_bearer_token"), - "concurrency": obj.get("concurrency"), - "cooldown_period": obj.get("cooldown_period") if obj.get("cooldown_period") is not None else 1800, - "env_vars": obj.get("env_vars"), - "env_vars_refs": obj.get("env_vars_refs"), - "bearer_token_ref": obj.get("bearer_token_ref"), - "enable_logging": obj.get("enable_logging") if obj.get("enable_logging") is not None else True, - "enable_node_model_cache": obj.get("enable_node_model_cache") if obj.get("enable_node_model_cache") is not None else False, - "session_affinity": obj.get("session_affinity") if obj.get("session_affinity") is not None else False - }) - return _obj - - diff --git a/platform_api_python_client/models/get_dynamo_deployment_response.py b/platform_api_python_client/models/get_dynamo_deployment_response.py index 29b83a9..5a08a07 100644 --- a/platform_api_python_client/models/get_dynamo_deployment_response.py +++ b/platform_api_python_client/models/get_dynamo_deployment_response.py @@ -26,6 +26,7 @@ from platform_api_python_client.models.deployment_type import DeploymentType from platform_api_python_client.models.dynamo_communications_output import DynamoCommunicationsOutput from platform_api_python_client.models.dynamo_serving_mode import DynamoServingMode +from platform_api_python_client.models.dynamo_weight_transfer_configuration import DynamoWeightTransferConfiguration from platform_api_python_client.models.dynamo_worker_pools import DynamoWorkerPools from platform_api_python_client.models.volume_mount import VolumeMount from typing import Optional, Set @@ -54,7 +55,9 @@ class GetDynamoDeploymentResponse(BaseModel): serving_mode: Optional[DynamoServingMode] = None worker_pools: Optional[DynamoWorkerPools] = None communications: Optional[DynamoCommunicationsOutput] = None + weight_transfer: Optional[DynamoWeightTransferConfiguration] = None model: StrictStr + model_revision: Optional[StrictStr] = None served_model_name: Optional[StrictStr] = None runtime_version: Optional[StrictStr] = None min_replicas: StrictInt = Field(description="Deprecated aggregated-only spelling; set this under worker_pools.worker instead. Accepted alongside worker_pools when the values agree.") @@ -71,7 +74,7 @@ class GetDynamoDeploymentResponse(BaseModel): enable_logging: Optional[StrictBool] = True enable_node_model_cache: Optional[StrictBool] = False backend_protocol: Optional[BackendProtocol] = None - __properties: ClassVar[List[str]] = ["creator_email", "cluster_id", "id", "name", "endpoint_url", "image_url", "type", "status", "created_at", "hardware_instance_id", "revision_number", "chart_revision", "user_annotations", "priority", "volume_mounts", "hf_token_ref", "serving_mode", "worker_pools", "communications", "model", "served_model_name", "runtime_version", "min_replicas", "max_replicas", "concurrency", "cooldown_period", "extra_args", "env_vars", "env_vars_refs", "endpoint_certificate_authority", "endpoint_bearer_token", "bearer_token_ref", "image_pull_ref", "enable_logging", "enable_node_model_cache", "backend_protocol"] + __properties: ClassVar[List[str]] = ["creator_email", "cluster_id", "id", "name", "endpoint_url", "image_url", "type", "status", "created_at", "hardware_instance_id", "revision_number", "chart_revision", "user_annotations", "priority", "volume_mounts", "hf_token_ref", "serving_mode", "worker_pools", "communications", "weight_transfer", "model", "model_revision", "served_model_name", "runtime_version", "min_replicas", "max_replicas", "concurrency", "cooldown_period", "extra_args", "env_vars", "env_vars_refs", "endpoint_certificate_authority", "endpoint_bearer_token", "bearer_token_ref", "image_pull_ref", "enable_logging", "enable_node_model_cache", "backend_protocol"] model_config = ConfigDict( populate_by_name=True, @@ -125,6 +128,9 @@ def to_dict(self) -> Dict[str, Any]: # override the default output from pydantic by calling `to_dict()` of communications if self.communications: _dict['communications'] = self.communications.to_dict() + # override the default output from pydantic by calling `to_dict()` of weight_transfer + if self.weight_transfer: + _dict['weight_transfer'] = self.weight_transfer.to_dict() # set to None if image_url (nullable) is None # and model_fields_set contains the field if self.image_url is None and "image_url" in self.model_fields_set: @@ -160,6 +166,16 @@ def to_dict(self) -> Dict[str, Any]: if self.communications is None and "communications" in self.model_fields_set: _dict['communications'] = None + # set to None if weight_transfer (nullable) is None + # and model_fields_set contains the field + if self.weight_transfer is None and "weight_transfer" in self.model_fields_set: + _dict['weight_transfer'] = None + + # set to None if model_revision (nullable) is None + # and model_fields_set contains the field + if self.model_revision is None and "model_revision" in self.model_fields_set: + _dict['model_revision'] = None + # set to None if served_model_name (nullable) is None # and model_fields_set contains the field if self.served_model_name is None and "served_model_name" in self.model_fields_set: @@ -236,7 +252,9 @@ def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]: "serving_mode": obj.get("serving_mode"), "worker_pools": DynamoWorkerPools.from_dict(obj["worker_pools"]) if obj.get("worker_pools") is not None else None, "communications": DynamoCommunicationsOutput.from_dict(obj["communications"]) if obj.get("communications") is not None else None, + "weight_transfer": DynamoWeightTransferConfiguration.from_dict(obj["weight_transfer"]) if obj.get("weight_transfer") is not None else None, "model": obj.get("model"), + "model_revision": obj.get("model_revision"), "served_model_name": obj.get("served_model_name"), "runtime_version": obj.get("runtime_version"), "min_replicas": obj.get("min_replicas"), diff --git a/pyproject.toml b/pyproject.toml index 17f2217..96dd68c 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "platform_api_python_client" -version = "4.36.0" +version = "4.37.0" description = "Platform External API" authors = ["OpenAPI Generator Community "] license = "NoLicense" diff --git a/setup.py b/setup.py index 5dc9508..e7af22f 100644 --- a/setup.py +++ b/setup.py @@ -21,7 +21,7 @@ # prerequisite: setuptools # http://pypi.python.org/pypi/setuptools NAME = "platform-api-python-client" -VERSION = "4.36.0" +VERSION = "4.37.0" PYTHON_REQUIRES = ">= 3.8" REQUIRES = [ "urllib3 >= 1.25.3, < 3.0.0", diff --git a/test/test_create_c_serve_v2_deployment_response.py b/test/test_create_c_serve_v2_deployment_response.py deleted file mode 100644 index 2e3ff94..0000000 --- a/test/test_create_c_serve_v2_deployment_response.py +++ /dev/null @@ -1,56 +0,0 @@ -# coding: utf-8 - -""" - Platform External API - - No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) - - The version of the OpenAPI document: 0.1.0 - Generated by OpenAPI Generator (https://openapi-generator.tech) - - Do not edit the class manually. -""" # noqa: E501 - - -import unittest - -from platform_api_python_client.models.create_c_serve_v2_deployment_response import CreateCServeV2DeploymentResponse - -class TestCreateCServeV2DeploymentResponse(unittest.TestCase): - """CreateCServeV2DeploymentResponse unit test stubs""" - - def setUp(self): - pass - - def tearDown(self): - pass - - def make_instance(self, include_optional) -> CreateCServeV2DeploymentResponse: - """Test CreateCServeV2DeploymentResponse - include_optional is a boolean, when False only required - params are included, when True both required and - optional params are included """ - # uncomment below to create an instance of `CreateCServeV2DeploymentResponse` - """ - model = CreateCServeV2DeploymentResponse() - if include_optional: - return CreateCServeV2DeploymentResponse( - id = 56, - created_at = datetime.datetime.strptime('2013-10-20 19:20:30.00', '%Y-%m-%d %H:%M:%S.%f'), - endpoint_url = '' - ) - else: - return CreateCServeV2DeploymentResponse( - id = 56, - created_at = datetime.datetime.strptime('2013-10-20 19:20:30.00', '%Y-%m-%d %H:%M:%S.%f'), - endpoint_url = '', - ) - """ - - def testCreateCServeV2DeploymentResponse(self): - """Test CreateCServeV2DeploymentResponse""" - # inst_req_only = self.make_instance(include_optional=False) - # inst_req_and_optional = self.make_instance(include_optional=True) - -if __name__ == '__main__': - unittest.main() diff --git a/test/test_create_c_serve_v3_deployment_request.py b/test/test_create_c_serve_v3_deployment_request.py deleted file mode 100644 index fa89e60..0000000 --- a/test/test_create_c_serve_v3_deployment_request.py +++ /dev/null @@ -1,94 +0,0 @@ -# coding: utf-8 - -""" - Platform External API - - No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) - - The version of the OpenAPI document: 0.1.0 - Generated by OpenAPI Generator (https://openapi-generator.tech) - - Do not edit the class manually. -""" # noqa: E501 - - -import unittest - -from platform_api_python_client.models.create_c_serve_v3_deployment_request import CreateCServeV3DeploymentRequest - -class TestCreateCServeV3DeploymentRequest(unittest.TestCase): - """CreateCServeV3DeploymentRequest unit test stubs""" - - def setUp(self): - pass - - def tearDown(self): - pass - - def make_instance(self, include_optional) -> CreateCServeV3DeploymentRequest: - """Test CreateCServeV3DeploymentRequest - include_optional is a boolean, when False only required - params are included, when True both required and - optional params are included """ - # uncomment below to create an instance of `CreateCServeV3DeploymentRequest` - """ - model = CreateCServeV3DeploymentRequest() - if include_optional: - return CreateCServeV3DeploymentRequest( - max_surge = 56, - max_unavailable = 56, - name = 'ar1c2v7s6djuy1zmetozkhdomha1b0', - cluster_id = 56, - hardware_instance_id = 56, - user_annotations = { - 'key' : '' - }, - chart_revision = '', - volume_mounts = [ - platform_api_python_client.models.volume_mount.VolumeMount( - volume_id = 56, - mount_path = '0', - read_only = True, ) - ], - priority = '', - hf_token_ref = 1.0, - recipe = { - 'key' : null - }, - cserve_version = '', - hf_token = '', - endpoint_bearer_token = '', - bearer_token_ref = 1.0, - endpoint_certificate_authority = '', - min_replicas = 56, - max_replicas = 56, - concurrency = 56, - cooldown_period = 0.0, - env_vars = { - 'key' : '' - }, - env_vars_refs = platform_api_python_client.models.env_vars_refs.Env Vars Refs(), - enable_logging = True, - enable_node_model_cache = True, - session_affinity = True - ) - else: - return CreateCServeV3DeploymentRequest( - name = 'ar1c2v7s6djuy1zmetozkhdomha1b0', - cluster_id = 56, - hardware_instance_id = 56, - recipe = { - 'key' : null - }, - min_replicas = 56, - max_replicas = 56, - ) - """ - - def testCreateCServeV3DeploymentRequest(self): - """Test CreateCServeV3DeploymentRequest""" - # inst_req_only = self.make_instance(include_optional=False) - # inst_req_and_optional = self.make_instance(include_optional=True) - -if __name__ == '__main__': - unittest.main() diff --git a/test/test_create_c_serve_v3_deployment_response.py b/test/test_create_c_serve_v3_deployment_response.py deleted file mode 100644 index 025b6ea..0000000 --- a/test/test_create_c_serve_v3_deployment_response.py +++ /dev/null @@ -1,56 +0,0 @@ -# coding: utf-8 - -""" - Platform External API - - No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) - - The version of the OpenAPI document: 0.1.0 - Generated by OpenAPI Generator (https://openapi-generator.tech) - - Do not edit the class manually. -""" # noqa: E501 - - -import unittest - -from platform_api_python_client.models.create_c_serve_v3_deployment_response import CreateCServeV3DeploymentResponse - -class TestCreateCServeV3DeploymentResponse(unittest.TestCase): - """CreateCServeV3DeploymentResponse unit test stubs""" - - def setUp(self): - pass - - def tearDown(self): - pass - - def make_instance(self, include_optional) -> CreateCServeV3DeploymentResponse: - """Test CreateCServeV3DeploymentResponse - include_optional is a boolean, when False only required - params are included, when True both required and - optional params are included """ - # uncomment below to create an instance of `CreateCServeV3DeploymentResponse` - """ - model = CreateCServeV3DeploymentResponse() - if include_optional: - return CreateCServeV3DeploymentResponse( - id = 56, - created_at = datetime.datetime.strptime('2013-10-20 19:20:30.00', '%Y-%m-%d %H:%M:%S.%f'), - endpoint_url = '' - ) - else: - return CreateCServeV3DeploymentResponse( - id = 56, - created_at = datetime.datetime.strptime('2013-10-20 19:20:30.00', '%Y-%m-%d %H:%M:%S.%f'), - endpoint_url = '', - ) - """ - - def testCreateCServeV3DeploymentResponse(self): - """Test CreateCServeV3DeploymentResponse""" - # inst_req_only = self.make_instance(include_optional=False) - # inst_req_and_optional = self.make_instance(include_optional=True) - -if __name__ == '__main__': - unittest.main() diff --git a/test/test_create_dynamo_deployment_request.py b/test/test_create_dynamo_deployment_request.py index 2c18f60..8bb5e64 100644 --- a/test/test_create_dynamo_deployment_request.py +++ b/test/test_create_dynamo_deployment_request.py @@ -71,7 +71,10 @@ def make_instance(self, include_optional) -> CreateDynamoDeploymentRequest: communications = platform_api_python_client.models.dynamo_communications.DynamoCommunications( kv_transfer = platform_api_python_client.models.dynamo_kv_transfer_configuration.DynamoKvTransferConfiguration( policy = 'allow_tcp', ), ), + weight_transfer = platform_api_python_client.models.dynamo_weight_transfer_configuration.DynamoWeightTransferConfiguration( + policy = 'require_gpu_direct_rdma', ), model = '', + model_revision = '0', served_model_name = '', runtime_version = 'e6bUUGjjNSwg0_bs9ZayIMrKdgNvb6gvxmPb9GcsM61ate1RA89q3w1l4eH4XxEz.5awxoFZxHzs6ED.kjUSnTINkYPUndNl8pmPg5K897Fu1JEFj9R1_dz9rEoBi0L', min_replicas = 56, diff --git a/test/test_deployment_response.py b/test/test_deployment_response.py index 762b84d..24ff741 100644 --- a/test/test_deployment_response.py +++ b/test/test_deployment_response.py @@ -78,7 +78,10 @@ def make_instance(self, include_optional) -> DeploymentResponse: communications = platform_api_python_client.models.dynamo_communications.DynamoCommunications( kv_transfer = platform_api_python_client.models.dynamo_kv_transfer_configuration.DynamoKvTransferConfiguration( policy = 'allow_tcp', ), ), + weight_transfer = platform_api_python_client.models.dynamo_weight_transfer_configuration.DynamoWeightTransferConfiguration( + policy = 'require_gpu_direct_rdma', ), model = '', + model_revision = '', served_model_name = '', runtime_version = '', min_replicas = 56, @@ -97,11 +100,6 @@ def make_instance(self, include_optional) -> DeploymentResponse: enable_logging = True, enable_node_model_cache = True, backend_protocol = 'HTTP', - recipe = { - 'key' : null - }, - cserve_version = '', - session_affinity = True, container_port = 56, healthcheck = '', command = [ @@ -115,6 +113,7 @@ def make_instance(self, include_optional) -> DeploymentResponse: username = '', password = '', ), image_pull_secret_name = 'w1c2v7s6djuy1zmetozkhdomha1bae37b8ocvx8o53ow2eg7p6qw9qklp6l4y010fogx.mjvnh6nzn2yp6d7tmo7zxedi-pkbmhcbu-4d4ncp9sp-gpju7f9r1ly-n2jyba-zuswj171d3kxld4uyykb66fgvcwlw.s.p6div96l1hmssf5by0949ps5we2h1m5s.4.7ftu50o3hq25-ctix-xt8fyuzw85-6ya.ezgfzdm4groy.ccn4nxdzyngfr2bsdqi-90qr77qnqf26kpzuf5a652r9yc8wgc.uoko8ht4bjsb-86ca0gq8ejs584qp107f5qv9ze3gk7q64-5mecujmelufynb1wtb8v2n1x9-y9o36a.uqixpalso4ehay1yebs1kiembt-homr2.864bew-vpjuuty7-xv4qjygg3hwqd-5gynywalvhvvesyveyxp35spjahpsiagrj0jehh3a3x8z9axqtswj383252z.d6d4ifob3rgi7j1fao-vb9l55lz.bsk1mqype9zx3n6q-u55t879v1lf.1.k.isf-swgdlh.0.m4u5aoqakjc4xlcmbpoy4ndizk4s3cdhxttexawd8mnl6e4uzxalowdqy9rokd32ct-w5p-yt-emwrzfi.lulqkw0osnqktff9fp6xbt97440w4wt3xjayovyb7flljlnosgtrofp.o.j.p5-2p577rg1fwny6cq1e2d3p5aa62rscqk6cxzeqcrvjnbqd52lumjr3qda19c-7skjef4ovphp57sme4j.v.ex0xp4ft9xd1-4zvmus0m5p.v0h-jlvu47xor814uas43gvg7px7mohsvz1n3b561az73nipt-so37iphbtnhmw48ibn.m.bk41trymo7d0ea3vl3k8vn3ygn2a7ps3-pdkhjjxrdr3lz6urrzqtzh9wngf-95dvz5km9h9e5j8vg6kx1nnqzi442akggqdhy6.i.gupb4cz72xp4qgqp5jsd55qux2vq83uq1j9iy-qb4bt8kb625gpncppm1zw5yrhj.5q6soeyc3hzdpj1thb.b.b5xq79rwp3km1p11ikuwgghy12wdp5xrrsyrsnl7yjolek10nb0oh.h.x.2h707s1vjswprq6au.xucdr85u0erh5dfg2hvs9u7vn0y8ci0w5cs0m66nvcce2fr52dkbd9-7klkniu5cpn6qugmep5e6p9gx9creyetm.2sgithzei3bx4-4ox6m2aiffxmcwza92oxtwxs76a.s.z.im-3mvtf47ak-ld.a.2elgcf13ovinqusgnnclaaotmbqdseafe1dkj6zg4q-zexx0zm-n.j3-w17r6rxur1pbea75jjl8lv5xitcozp.c.h.61bftab5cre-v.9.v.s.fyenvbtf508c5c3k.mghqe7lyva958ar2bzuf2507k602lnujv0ps2icyh27nxstaqbg38m0hpe.g.bg8n69rdva8j104ap-cf1p9yc1ijk9np17sjmh2tukz4atwz0044pdhk9pk1eft1nod0p9-vepbljhwtpf-qd2ysm1.3tiane3jk-09bf0q3dbgqocrp16dzj0xk-uyej17sd81mbgu820re53g21e779vy6.z.rm8pn0xdthfd9cqpo9sslxeml661r0eol4jypf6mdna86sfgz92k.y-52xiufg9mfli1bjvsy947g3cz7wufbd001uiwvuaxblt37i0ah0z6f6qhqwar1c3r14v-vt3pd5kbrrs94okiob2jznknec6ky.3.d.dgp-oapce410llsnx-m--ufb725icarr8pijimdu9gxv3p7744x7btxc9-zq66zjny7rvcbdfcl-7ksv-awu1ddn3dlag.1cg4obm9r3waeqrdsk53.1.q.k.w.gz5qwr2rjf1o2625v873inyqekdlul-2yu96dhuposmz433w4216crklr6.5ifmkesrrzj9hbtdyamuoxl0l1gb0vgsms5ou3nfhhnvvfktn2uyclzyqvy90vz11a6oipnv4tno7.z.t.u4pfk1y-f41a9ekyw5sfqgxxg2436imo6t94jmeph0msaf6p04q5p6z75n97ibih9ynp9w52m2.7bh985by7-jms7z9rzl84e9iub-3gwwq4fe81bi2bmela-4-ti6-mqq-em0m73ls976osz80kxxj.x.jxe4zxgit8guso2bynf9xkxywffvyznse5yovoes9zqhgf9wk74po4qj1hri4b.06kv2f-9nff.ejas130ndgnxp85h0saokre-wcp8nl4iio.g.z8c-0hnu2tn0fal1tsn8phrmhzoys2l25i7fgxqn8.w.w.z0', + session_affinity = True, config_file = platform_api_python_client.models.config_file_mount.ConfigFileMount( filename = '20', mount_path = '0', @@ -148,9 +147,6 @@ def make_instance(self, include_optional) -> DeploymentResponse: model = '', min_replicas = 56, max_replicas = 56, - recipe = { - 'key' : null - }, container_port = 56, exposed_port = 56, ) diff --git a/test/test_c_serve_v2_recipe.py b/test/test_dynamo_weight_transfer_configuration.py similarity index 53% rename from test/test_c_serve_v2_recipe.py rename to test/test_dynamo_weight_transfer_configuration.py index 136bc53..00c836b 100644 --- a/test/test_c_serve_v2_recipe.py +++ b/test/test_dynamo_weight_transfer_configuration.py @@ -14,10 +14,10 @@ import unittest -from platform_api_python_client.models.c_serve_v2_recipe import CServeV2Recipe +from platform_api_python_client.models.dynamo_weight_transfer_configuration import DynamoWeightTransferConfiguration -class TestCServeV2Recipe(unittest.TestCase): - """CServeV2Recipe unit test stubs""" +class TestDynamoWeightTransferConfiguration(unittest.TestCase): + """DynamoWeightTransferConfiguration unit test stubs""" def setUp(self): pass @@ -25,28 +25,25 @@ def setUp(self): def tearDown(self): pass - def make_instance(self, include_optional) -> CServeV2Recipe: - """Test CServeV2Recipe + def make_instance(self, include_optional) -> DynamoWeightTransferConfiguration: + """Test DynamoWeightTransferConfiguration include_optional is a boolean, when False only required params are included, when True both required and optional params are included """ - # uncomment below to create an instance of `CServeV2Recipe` + # uncomment below to create an instance of `DynamoWeightTransferConfiguration` """ - model = CServeV2Recipe() + model = DynamoWeightTransferConfiguration() if include_optional: - return CServeV2Recipe( - model = '', - revision = '', - is_embedding_model = True + return DynamoWeightTransferConfiguration( + policy = 'require_gpu_direct_rdma' ) else: - return CServeV2Recipe( - model = '', + return DynamoWeightTransferConfiguration( ) """ - def testCServeV2Recipe(self): - """Test CServeV2Recipe""" + def testDynamoWeightTransferConfiguration(self): + """Test DynamoWeightTransferConfiguration""" # inst_req_only = self.make_instance(include_optional=False) # inst_req_and_optional = self.make_instance(include_optional=True) diff --git a/test/test_dynamo_weight_transfer_policy.py b/test/test_dynamo_weight_transfer_policy.py new file mode 100644 index 0000000..6c2221d --- /dev/null +++ b/test/test_dynamo_weight_transfer_policy.py @@ -0,0 +1,33 @@ +# coding: utf-8 + +""" + Platform External API + + No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) + + The version of the OpenAPI document: 0.1.0 + Generated by OpenAPI Generator (https://openapi-generator.tech) + + Do not edit the class manually. +""" # noqa: E501 + + +import unittest + +from platform_api_python_client.models.dynamo_weight_transfer_policy import DynamoWeightTransferPolicy + +class TestDynamoWeightTransferPolicy(unittest.TestCase): + """DynamoWeightTransferPolicy unit test stubs""" + + def setUp(self): + pass + + def tearDown(self): + pass + + def testDynamoWeightTransferPolicy(self): + """Test DynamoWeightTransferPolicy""" + # inst = DynamoWeightTransferPolicy() + +if __name__ == '__main__': + unittest.main() diff --git a/test/test_external_api.py b/test/test_external_api.py index 29eeaa8..0e1e656 100644 --- a/test/test_external_api.py +++ b/test/test_external_api.py @@ -40,17 +40,24 @@ def test_create_compute_deployment_deployments_compute_post(self) -> None: """ pass + def test_create_cserve_deployment_deployments_cserve_post(self) -> None: + """Test case for create_cserve_deployment_deployments_cserve_post + + Retired Cserve Deployment + """ + pass + def test_create_cserve_v2_deployment_deployments_cserve_v2_post(self) -> None: """Test case for create_cserve_v2_deployment_deployments_cserve_v2_post - Create Cserve V2 Deployment + Retired Cserve Deployment """ pass def test_create_cserve_v3_deployment_deployments_cserve_v3_post(self) -> None: """Test case for create_cserve_v3_deployment_deployments_cserve_v3_post - Create Cserve V3 Deployment + Retired Cserve Deployment """ pass @@ -208,17 +215,24 @@ def test_get_credits_credits_get(self) -> None: """ pass + def test_get_cserve_deployment_deployments_cserve_deployment_id_get(self) -> None: + """Test case for get_cserve_deployment_deployments_cserve_deployment_id_get + + Retired Cserve Deployment Detail + """ + pass + def test_get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get(self) -> None: """Test case for get_cserve_v2_deployment_deployments_cserve_v2_deployment_id_get - Get Cserve V2 Deployment + Retired Cserve Deployment Detail """ pass def test_get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get(self) -> None: """Test case for get_cserve_v3_deployment_deployments_cserve_v3_deployment_id_get - Get Cserve V3 Deployment + Retired Cserve Deployment Detail """ pass @@ -523,17 +537,24 @@ def test_update_compute_deployment_deployments_compute_put(self) -> None: """ pass + def test_update_cserve_deployment_deployments_cserve_put(self) -> None: + """Test case for update_cserve_deployment_deployments_cserve_put + + Retired Cserve Deployment + """ + pass + def test_update_cserve_v2_deployment_deployments_cserve_v2_put(self) -> None: """Test case for update_cserve_v2_deployment_deployments_cserve_v2_put - Update Cserve V2 Deployment + Retired Cserve Deployment """ pass def test_update_cserve_v3_deployment_deployments_cserve_v3_put(self) -> None: """Test case for update_cserve_v3_deployment_deployments_cserve_v3_put - Update Cserve V3 Deployment + Retired Cserve Deployment """ pass diff --git a/test/test_get_c_serve_v2_deployment_response.py b/test/test_get_c_serve_v2_deployment_response.py deleted file mode 100644 index ede2ead..0000000 --- a/test/test_get_c_serve_v2_deployment_response.py +++ /dev/null @@ -1,100 +0,0 @@ -# coding: utf-8 - -""" - Platform External API - - No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) - - The version of the OpenAPI document: 0.1.0 - Generated by OpenAPI Generator (https://openapi-generator.tech) - - Do not edit the class manually. -""" # noqa: E501 - - -import unittest - -from platform_api_python_client.models.get_c_serve_v2_deployment_response import GetCServeV2DeploymentResponse - -class TestGetCServeV2DeploymentResponse(unittest.TestCase): - """GetCServeV2DeploymentResponse unit test stubs""" - - def setUp(self): - pass - - def tearDown(self): - pass - - def make_instance(self, include_optional) -> GetCServeV2DeploymentResponse: - """Test GetCServeV2DeploymentResponse - include_optional is a boolean, when False only required - params are included, when True both required and - optional params are included """ - # uncomment below to create an instance of `GetCServeV2DeploymentResponse` - """ - model = GetCServeV2DeploymentResponse() - if include_optional: - return GetCServeV2DeploymentResponse( - creator_email = '', - cluster_id = 56, - id = 56, - name = '', - endpoint_url = '', - image_url = '', - type = 'inference', - status = 'active', - created_at = datetime.datetime.strptime('2013-10-20 19:20:30.00', '%Y-%m-%d %H:%M:%S.%f'), - hardware_instance_id = 56, - revision_number = 56, - chart_revision = '', - user_annotations = { - 'key' : '' - }, - priority = '', - volume_mounts = [ - platform_api_python_client.models.volume_mount.VolumeMount( - volume_id = 56, - mount_path = '0', - read_only = True, ) - ], - recipe = { - 'key' : null - }, - cserve_version = '', - min_scale = 56, - max_scale = 56, - initial_scale = 56, - endpoint_certificate_authority = '', - endpoint_bearer_token = '', - concurrency = 56, - env_vars = { - 'key' : '' - } - ) - else: - return GetCServeV2DeploymentResponse( - creator_email = '', - cluster_id = 56, - id = 56, - name = '', - endpoint_url = '', - type = 'inference', - status = 'active', - created_at = datetime.datetime.strptime('2013-10-20 19:20:30.00', '%Y-%m-%d %H:%M:%S.%f'), - hardware_instance_id = 56, - revision_number = 56, - recipe = { - 'key' : null - }, - min_scale = 56, - max_scale = 56, - ) - """ - - def testGetCServeV2DeploymentResponse(self): - """Test GetCServeV2DeploymentResponse""" - # inst_req_only = self.make_instance(include_optional=False) - # inst_req_and_optional = self.make_instance(include_optional=True) - -if __name__ == '__main__': - unittest.main() diff --git a/test/test_get_c_serve_v3_deployment_response.py b/test/test_get_c_serve_v3_deployment_response.py deleted file mode 100644 index a4de92b..0000000 --- a/test/test_get_c_serve_v3_deployment_response.py +++ /dev/null @@ -1,106 +0,0 @@ -# coding: utf-8 - -""" - Platform External API - - No description provided (generated by Openapi Generator https://github.com/openapitools/openapi-generator) - - The version of the OpenAPI document: 0.1.0 - Generated by OpenAPI Generator (https://openapi-generator.tech) - - Do not edit the class manually. -""" # noqa: E501 - - -import unittest - -from platform_api_python_client.models.get_c_serve_v3_deployment_response import GetCServeV3DeploymentResponse - -class TestGetCServeV3DeploymentResponse(unittest.TestCase): - """GetCServeV3DeploymentResponse unit test stubs""" - - def setUp(self): - pass - - def tearDown(self): - pass - - def make_instance(self, include_optional) -> GetCServeV3DeploymentResponse: - """Test GetCServeV3DeploymentResponse - include_optional is a boolean, when False only required - params are included, when True both required and - optional params are included """ - # uncomment below to create an instance of `GetCServeV3DeploymentResponse` - """ - model = GetCServeV3DeploymentResponse() - if include_optional: - return GetCServeV3DeploymentResponse( - creator_email = '', - cluster_id = 56, - id = 56, - name = '', - endpoint_url = '', - image_url = '', - type = 'inference', - status = 'active', - created_at = datetime.datetime.strptime('2013-10-20 19:20:30.00', '%Y-%m-%d %H:%M:%S.%f'), - hardware_instance_id = 56, - revision_number = 56, - chart_revision = '', - user_annotations = { - 'key' : '' - }, - priority = '', - volume_mounts = [ - platform_api_python_client.models.volume_mount.VolumeMount( - volume_id = 56, - mount_path = '0', - read_only = True, ) - ], - hf_token_ref = 1.0, - recipe = { - 'key' : null - }, - cserve_version = '', - min_replicas = 56, - max_replicas = 56, - endpoint_certificate_authority = '', - endpoint_bearer_token = '', - concurrency = 56, - cooldown_period = 56, - env_vars = { - 'key' : '' - }, - env_vars_refs = platform_api_python_client.models.env_vars_refs.Env Vars Refs(), - bearer_token_ref = 1.0, - enable_logging = True, - enable_node_model_cache = True, - session_affinity = True - ) - else: - return GetCServeV3DeploymentResponse( - creator_email = '', - cluster_id = 56, - id = 56, - name = '', - endpoint_url = '', - type = 'inference', - status = 'active', - created_at = datetime.datetime.strptime('2013-10-20 19:20:30.00', '%Y-%m-%d %H:%M:%S.%f'), - hardware_instance_id = 56, - revision_number = 56, - recipe = { - 'key' : null - }, - min_replicas = 56, - max_replicas = 56, - ) - """ - - def testGetCServeV3DeploymentResponse(self): - """Test GetCServeV3DeploymentResponse""" - # inst_req_only = self.make_instance(include_optional=False) - # inst_req_and_optional = self.make_instance(include_optional=True) - -if __name__ == '__main__': - unittest.main() diff --git a/test/test_get_dynamo_deployment_response.py b/test/test_get_dynamo_deployment_response.py index 44b59ae..94ad72f 100644 --- a/test/test_get_dynamo_deployment_response.py +++ b/test/test_get_dynamo_deployment_response.py @@ -78,7 +78,10 @@ def make_instance(self, include_optional) -> GetDynamoDeploymentResponse: communications = platform_api_python_client.models.dynamo_communications.DynamoCommunications( kv_transfer = platform_api_python_client.models.dynamo_kv_transfer_configuration.DynamoKvTransferConfiguration( policy = 'allow_tcp', ), ), + weight_transfer = platform_api_python_client.models.dynamo_weight_transfer_configuration.DynamoWeightTransferConfiguration( + policy = 'require_gpu_direct_rdma', ), model = '', + model_revision = '', served_model_name = '', runtime_version = '', min_replicas = 56,