Skip to content

Commit b37308e

Browse files
v-dirichardsv-dirichards
authored
Merge pull request #275927 from msakande/region-availability-for-models
update region availability for serverless API
2 parents f49e3e7 + 7d93ad4 commit b37308e

File tree

5 files changed

+103
-38
lines changed

5 files changed

+103
-38
lines changed

‎articles/ai-studio/how-to/deploy-models-serverless-availability.md

Lines changed: 6 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -6,17 +6,17 @@ manager: scottpolly
66
ms.service: azure-ai-studio
77
ms.topic: how-to
88
ms.date: 5/21/2024
9-
ms.reviewer: mopeakande
10-
reviewer: msakande
11-
ms.author: fasantia
12-
author: santiagxf
9+
ms.author: mopeakande
10+
author: msakande
11+
ms.reviewer: fasantia
12+
reviewer: santiagxf
1313
ms.custom:
1414
- build-2024
1515
- serverless
1616
- references_regions
1717
---
1818

19-
# Region availability for models in Serverless API endpoints | Azure AI Studio
19+
# Region availability for models in serverless API endpoints | Azure AI Studio
2020

2121
[!INCLUDE [Feature preview](../includes/feature-preview.md)]
2222

@@ -26,18 +26,7 @@ Certain models in the model catalog can be deployed as a serverless API with pay
2626

2727
## Region availability
2828

29-
Serverless API endpoints are available in the following regions for the indicated models:
30-
31-
| Model | East US 2 | West US 3 | Sweden Central | France Central |
32-
| ----------------- | ----------- | -------------- | -------------- | -------------- |
33-
| Mistral-Small | **✓** | | **✓** | |
34-
| Mistral-Large | **✓** | | **✓** | **✓** |
35-
| Cohere Command R | **✓** | | **✓** | |
36-
| Cohere Command R+ | **✓** | | **✓** | |
37-
| Cohere Embed v3 | **✓** | | **✓** | |
38-
| Meta Llama 2 | **✓** | **✓** | | |
39-
| Meta Llama 3 | **✓** | | | |
40-
| Phi-3 | **✓** | | **✓** | |
29+
[!INCLUDE [region-availabilitity-serverless-api](../includes/region-availabilitity-serverless-api.md)]
4130

4231
## Alternatives to region availability
4332

‎articles/ai-studio/how-to/deploy-models-timegen-1.md

Lines changed: 12 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -31,10 +31,18 @@ You can deploy TimeGEN-1 as a serverless API with pay-as-you-go billing. Nixtla
3131
### Prerequisites
3232

3333
- An Azure subscription with a valid payment method. Free or trial Azure subscriptions don't work. If you don't have an Azure subscription, create a [paid Azure account](https://azure.microsoft.com/pricing/purchase-options/pay-as-you-go) to begin.
34-
- An [AI Studio hub](../how-to/create-azure-ai-resource.md).
34+
- An [AI Studio hub](../how-to/create-azure-ai-resource.md). The serverless API model deployment offering for TimeGEN-1 is only available with hubs created in these regions:
3535

36-
> [!IMPORTANT]
37-
> The serverless API model deployment offering for TimeGEN-1 is only available with hubs created in the **East US 2** or **Sweden Central** regions.
36+
> [!div class="checklist"]
37+
> * East US
38+
> * East US 2
39+
> * North Central US
40+
> * South Central US
41+
> * West US
42+
> * West US 3
43+
> * Sweden Central
44+
45+
For a list of regions that are available for each of the models supporting serverless API endpoint deployments, see [Region availability for models in serverless API endpoints](deploy-models-serverless-availability.md).
3846

3947
- An [Azure AI Studio project](../how-to/create-projects.md).
4048
- Azure role-based access controls (Azure RBAC) are used to grant access to operations in Azure AI Studio. To perform the steps in this article, your user account must be assigned the __Azure AI Developer role__ on the resource group. For more information on permissions, visit [Role-based access control in Azure AI Studio](../concepts/rbac-ai-studio.md).
@@ -52,7 +60,7 @@ These steps demonstrate the deployment of TimeGEN-1. To create a deployment:
5260
1. Select **+ Create deployment**.
5361
1. Search for and select **TimeGEN-1**. to open the Model's Details page.
5462
1. Select **Confirm** to open a serverless API deployment window for the model.
55-
1. Select the project in which you want to deploy your model. To deploy the TimeGEN-1 model, your project must be in the **East US 2** or **Sweden Central** region.
63+
1. Select the project in which you want to deploy your model. To deploy the TimeGEN-1 model, your project must be in one of the regions listed in the [Prerequisites](#prerequisites) section.
5664
1. In the deployment wizard, select the link to **Azure Marketplace Terms**, to learn more about the terms of use.
5765
1. Select the **Pricing and terms** tab to learn about pricing for the selected model.
5866
1. Select the **Subscribe and Deploy** button. If this is your first time deploying the model in the project, you have to subscribe your project for the particular offering. This step requires that your account has the **Azure AI Developer role** permissions on the resource group, as listed in the prerequisites. Each project has its own subscription to the particular Azure Marketplace offering of the model, which allows you to control and monitor spending. Currently, you can have only one deployment for each model within a project.

‎articles/ai-studio/includes/region-availabilitity-serverless-api.md

Lines changed: 71 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,71 @@
1+
---
2+
title: include file
3+
description: include file
4+
ms.service: azure-ai-studio
5+
ms.topic: include
6+
ms.date: 05/21/2024
7+
ms.author: mopeakande
8+
author: msakande
9+
ms.reviewer: fasantia
10+
reviewer: santiagxf
11+
ms.custom: include file
12+
13+
# Also used in Azure Machine Learning documentation
14+
---
15+
16+
Availability of serverless API endpoints for select models are listed in the following tables:
17+
18+
<!-- | Model | East US | East US 2 | North Central US | South Central US | West US | West US 3 | France Central | Sweden Central |
19+
|:-----------------:|:-----------:|:-----------:|:----------------:|:----------------:|:-----------:|:-----------:|:--------------:|:--------------:|
20+
| Mistral-Small | | **&check;** | | | | | | **&check;** |
21+
| Mistral-Large | | **&check;** | | | | | **&check;** | **&check;** |
22+
| Cohere Command R | | **&check;** | | | | | | **&check;** |
23+
| Cohere Command R+ | | **&check;** | | | | | | **&check;** |
24+
| Cohere Embed v3 | | **&check;** | | | | | | **&check;** |
25+
| Meta Llama 2 | | **&check;** | | | | **&check;** | | |
26+
| Meta Llama 3 | | **&check;** | | | | | | |
27+
| Phi-3 | | **&check;** | | | | | | **&check;** |
28+
| Nixtla TimeGEN-1 | **&check;** | **&check;** | **&check;** | **&check;** | **&check;** | **&check;** | | **&check;** | -->
29+
30+
31+
#### Cohere models
32+
33+
| Region | Cohere Command R | Cohere Command R+ | Cohere Embed v3 |
34+
|----------------|:----------------:|:-----------------:|:---------------:|
35+
| East US 2 | **&check;** | **&check;** | **&check;** |
36+
| Sweden Central | **&check;** | **&check;** | **&check;** |
37+
38+
#### Mistral models
39+
40+
| Region | Mistral-Small | Mistral-Large |
41+
|----------------|:-------------:|:-------------:|
42+
| East US 2 | **&check;** | **&check;** |
43+
| France Central | unavailable | **&check;** |
44+
| Sweden Central | **&check;** | **&check;** |
45+
46+
#### Meta Llama models
47+
48+
| Region | Llama-2 | Llama-3 |
49+
|-----------|:-----------:|:-----------:|
50+
| East US 2 | **&check;** | **&check;** |
51+
| West US 3 | **&check;** | unavailable |
52+
53+
#### Nixtla TimeGEN-1 model
54+
55+
| Region | Nixtla TimeGEN-1 |
56+
|------------------|:----------------:|
57+
| East US | **&check;** |
58+
| East US 2 | **&check;** |
59+
| North Central US | **&check;** |
60+
| South Central US | **&check;** |
61+
| West US | **&check;** |
62+
| West US 3 | **&check;** |
63+
| France Central | unavailable |
64+
| Sweden Central | **&check;** |
65+
66+
#### Phi 3 models
67+
68+
| Region | Phi 3 |
69+
|----------------|:-----------:|
70+
| East US 2 | **&check;** |
71+
| Sweden Central | **&check;** |

‎articles/machine-learning/concept-endpoint-serverless-availability.md

Lines changed: 2 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -17,26 +17,15 @@ ms.custom:
1717
- references_regions
1818
---
1919

20-
# Region availability for models in Serverless API endpoints | Azure Machine Learning
20+
# Region availability for models in serverless API endpoints | Azure Machine Learning
2121

2222
In this article, you learn about which regions are available for each of the models supporting serverless API endpoint deployments.
2323

2424
Certain models in the model catalog can be deployed as a serverless API with pay-as-you-go billing. This kind of deployment provides a way to consume models as an API without hosting them on your subscription, while keeping the enterprise security and compliance that organizations need. This deployment option doesn't require quota from your subscription.
2525

2626
## Region availability
2727

28-
Serverless API endpoints are available in the following regions for the indicated models:
29-
30-
| Model | East US 2 | West US 3 | Sweden Central | France Central |
31-
| ------------------ | ----------- | -------------- | -------------- | -------------- |
32-
| Mistral-Small | **&check;** | | **&check;** | |
33-
| Mistral-Large | **&check;** | | **&check;** | **&check;** |
34-
| Cohere Command R | **&check;** | | **&check;** | |
35-
| Cohere Command R+ | **&check;** | | **&check;** | |
36-
| Cohere Embed v3 | **&check;** | | **&check;** | |
37-
| Meta Llama 2 | **&check;** | **&check;** | | |
38-
| Meta Llama 3 | **&check;** | | | |
39-
| Phi-3 | **&check;** | | **&check;** | |
28+
[!INCLUDE [region-availabilitity-serverless-api](../ai-studio/includes/region-availabilitity-serverless-api.md)]
4029

4130
> [!NOTE]
4231
> Models offered through the Azure Marketplace are available for purchase only on [Microsoft Managed Countries](/partner-center/marketplace/tax-details-marketplace#microsoft-managed-countriesregions), with exception of Cohere family of models, which is also available in Japan.

‎articles/machine-learning/how-to-deploy-models-timegen-1.md

Lines changed: 12 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -32,10 +32,18 @@ You can deploy TimeGEN-1 as a serverless API with pay-as-you-go billing. Nixtla
3232
### Prerequisites
3333

3434
- An Azure subscription with a valid payment method. Free or trial Azure subscriptions don't work. If you don't have an Azure subscription, create a [paid Azure account](https://azure.microsoft.com/pricing/purchase-options/pay-as-you-go) to begin.
35-
- An Azure Machine Learning workspace. If you don't have a workspace, use the steps in the [Quickstart: Create workspace resources](quickstart-create-resources.md) article to create one.
35+
- An Azure Machine Learning workspace. If you don't have a workspace, use the steps in the [Quickstart: Create workspace resources](quickstart-create-resources.md) article to create one. The serverless API model deployment offering for TimeGEN-1 is only available with workspaces created in these regions:
3636

37-
> [!IMPORTANT]
38-
> The serverless API model deployment offering for TimeGEN-1 is only available with workspaces created in the **East US 2** or **Sweden Central** regions.
37+
> [!div class="checklist"]
38+
> * East US
39+
> * East US 2
40+
> * North Central US
41+
> * South Central US
42+
> * West US
43+
> * West US 3
44+
> * Sweden Central
45+
46+
For a list of regions that are available for each of the models supporting serverless API endpoint deployments, see [Region availability for models in serverless API endpoints](concept-endpoint-serverless-availability.md).
3947

4048
- Azure role-based access controls (Azure RBAC) are used to grant access to operations in Azure Machine Learning. To perform the steps in this article, your user account must be assigned the __Azure AI Developer role__ on the resource group. For more information on permissions, see [Manage access to an Azure Machine Learning workspace](how-to-assign-roles.md).
4149

@@ -45,7 +53,7 @@ You can deploy TimeGEN-1 as a serverless API with pay-as-you-go billing. Nixtla
4553
These steps demonstrate the deployment of TimeGEN-1. To create a deployment:
4654

4755
1. Go to [Azure Machine Learning studio](https://ml.azure.com/home).
48-
1. Select the workspace in which you want to deploy your models. To use the serverless API model deployment offering, your workspace must belong to the **East US 2** or **Sweden Central** region.
56+
1. Select the workspace in which you want to deploy your models. To use the serverless API model deployment offering, your workspace must belong to one of the regions listed in the [Prerequisites](#prerequisites) section.
4957
1. Choose the model **TimeGEN-1**, from the [model catalog](https://ml.azure.com/model/catalog).
5058
1. On the model's overview page in the model catalog, select **Deploy** to open up the serverless API deployment window.
5159

0 commit comments

Comments
 (0)