You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-foundry/concepts/encryption-keys-portal.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -87,7 +87,7 @@ Customer-managed key encryption is configured via Azure portal in a similar way
87
87
:::image type="content" source="../../machine-learning/media/concept-customer-managed-keys/cmk-service-side-encryption.png" alt-text="Screenshot of the encryption tab with the option for service side encryption selected." lightbox="../../machine-learning/media/concept-customer-managed-keys/cmk-service-side-encryption.png":::
88
88
89
89
Alternatively, use infrastructure-as-code options for automation. Example Bicep templates for Azure AI Foundry are available on the Azure Quickstart repo:
90
-
1.[CMK encryption for hub](https://github.com/Azure/azure-quickstart-templates/tree/master/quickstarts/microsoft.machinelearningservices/aistudio-cmk).
90
+
1.[CMK encryption for hub](https://github.com/Azure/azure-quickstart-templates/tree/master/quickstarts/microsoft.machinelearningservices/aifoundry-cmk).
91
91
1.[Service-side CMK encryption preview for hub](https://github.com/azure/azure-quickstart-templates/tree/master/quickstarts/microsoft.machinelearningservices/aistudio-cmk-service-side-encryption).
|[Mistral-small](https://ai.azure.com/explore/models/Mistral-small/version/1/registry/azureml-mistral)| March 31, 2025 | April 30, 2025 | July 31, 2025 |[Mistral-small-2503](https://aka.ms/aistudio/landing/mistral-small-2503)|
101
102
|[Mistral-large-2407](https://aka.ms/azureai/landing/Mistral-Large-2407)| January 13, 2025 | February 13, 2025 | May 13, 2025 |[Mistral-large-2411](https://aka.ms/aistudio/landing/Mistral-Large-2411)|
102
103
|[Mistral-large](https://aka.ms/azureai/landing/Mistral-Large)| December 15, 2024 | January 15, 2025 | April 15, 2025 |[Mistral-large-2411](https://aka.ms/aistudio/landing/Mistral-Large-2411)|
Copy file name to clipboardExpand all lines: articles/ai-foundry/concepts/models-featured.md
+7-2Lines changed: 7 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -246,16 +246,21 @@ For more examples of how to use Phi-3 family models, see the following examples:
246
246
247
247
## Mistral AI
248
248
249
-
Mistral AI offers two categories of models: premium models including Mistral Large and Mistral Small and open models including Mistral Nemo.
249
+
Mistral AI offers two categories of models, namely:
250
+
251
+
-_Premium models_: These include Mistral Large, Mistral Small, and Ministral 3B models, and are available as serverless APIs with pay-as-you-go token-based billing.
252
+
-_Open models_: These include Mistral-small-2503, Codestral, and Mistral Nemo (that are available as serverless APIs with pay-as-you-go token-based billing), and [Mixtral-8x7B-Instruct-v01, Mixtral-8x7B-v01, Mistral-7B-Instruct-v01, and Mistral-7B-v01](../how-to/deploy-models-mistral-open.md)(that are available to download and run on self-hosted managed endpoints).
253
+
250
254
251
255
| Model | Type | Capabilities |
252
256
| ------ | ---- | --- |
253
257
|[Codestral-2501](https://ai.azure.com/explore/models/Codestral-2501/version/2/registry/azureml-mistral)|[chat-completion](../model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context)| - **Input:** text (262,144 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Tool calling:** No <br /> - **Response formats:** Text |
Use a [Microsoft Bicep](/azure/azure-resource-manager/bicep/overview) template to create a hub for [Azure AI Foundry](https://ai.azure.com). A template makes it easy to create resources as a single, coordinated operation. A Bicep template is a text document that defines the resources that are needed for a deployment. It might also specify deployment parameters. Parameters are used to provide input values when using the template.
21
21
22
-
The template used in this article can be found at [https://github.com/Azure/azure-quickstart-templates/tree/master/quickstarts/microsoft.machinelearningservices/aistudio-basics](https://github.com/Azure/azure-quickstart-templates/tree/master/quickstarts/microsoft.machinelearningservices/aistudio-basics). Both the source `main.bicep` file and the compiled Azure Resource Manager template (`main.json`) file are available. This template creates the following resources:
22
+
The template used in this article can be found at [https://github.com/Azure/azure-quickstart-templates/tree/master/quickstarts/microsoft.machinelearningservices/aifoundry-basics](https://github.com/Azure/azure-quickstart-templates/tree/master/quickstarts/microsoft.machinelearningservices/aifoundry-basics). Both the source `main.bicep` file and the compiled Azure Resource Manager template (`main.json`) file are available. This template creates the following resources:
23
23
24
24
- An Azure resource group (if one doesn't already exist)
25
25
- An Azure AI Foundry hub
@@ -33,20 +33,20 @@ The template used in this article can be found at [https://github.com/Azure/azur
33
33
34
34
- An Azure subscription. If you don't have one, create a [free account](https://azure.microsoft.com/free/).
35
35
36
-
- A copy of the template files from the GitHub repo. To clone the GitHub repo to your local machine, you can use [Git](https://git-scm.com/). Use the following command to clone the quickstart repository to your local machine and navigate to the `aistudio-basics` directory.
36
+
- A copy of the template files from the GitHub repo. To clone the GitHub repo to your local machine, you can use [Git](https://git-scm.com/). Use the following command to clone the quickstart repository to your local machine and navigate to the `aifoundry-basics` directory.
cd azure-quickstart-templates\quickstarts\microsoft.machinelearningservices\aistudio-basics
49
+
cd azure-quickstart-templates\quickstarts\microsoft.machinelearningservices\aifoundry-basics
50
50
```
51
51
52
52
---
@@ -59,9 +59,9 @@ The Bicep template is made up of the following files:
59
59
60
60
| File | Description |
61
61
| ---- | ----------- |
62
-
| [main.bicep](https://github.com/Azure/azure-quickstart-templates/blob/master/quickstarts/microsoft.machinelearningservices/aistudio-basics/main.bicep) | The main Bicep file that defines the parameters and variables. Passing parameters & variables to other modules in the `modules` subdirectory. |
63
-
| [ai-hub.bicep](https://github.com/Azure/azure-quickstart-templates/blob/master/quickstarts/microsoft.machinelearningservices/aistudio-basics/modules/ai-hub.bicep) | Defines the hub. |
64
-
| [dependent-resources.bicep](https://github.com/Azure/azure-quickstart-templates/blob/master/quickstarts/microsoft.machinelearningservices/aistudio-basics/modules/dependent-resources.bicep) | Defines the dependent resources for the hub such as Azure Storage Account, Container Registry, Key Vault, and Application Insights. |
62
+
| [main.bicep](https://github.com/Azure/azure-quickstart-templates/blob/master/quickstarts/microsoft.machinelearningservices/aifoundry-basics/main.bicep) | The main Bicep file that defines the parameters and variables. Passing parameters & variables to other modules in the `modules` subdirectory. |
63
+
| [ai-hub.bicep](https://github.com/Azure/azure-quickstart-templates/blob/master/quickstarts/microsoft.machinelearningservices/aifoundry-basics/modules/ai-hub.bicep) | Defines the hub. |
64
+
| [dependent-resources.bicep](https://github.com/Azure/azure-quickstart-templates/blob/master/quickstarts/microsoft.machinelearningservices/aifoundry-basics/modules/dependent-resources.bicep) | Defines the dependent resources for the hub such as Azure Storage Account, Container Registry, Key Vault, and Application Insights. |
65
65
66
66
> [!IMPORTANT]
67
67
> The example templates might not always use the latest API version for the Azure resources it creates. Before using the template, we recommend modifying it to use the latest API versions. Each Azure service has its own set of API versions. For information on the API for a specific service, check the service information in the [Azure REST API reference](/rest/api/azure/).
@@ -85,7 +85,7 @@ For more information, see the [Bicep CLI](/azure/azure-resource-manager/bicep/bi
85
85
86
86
## Configure the template
87
87
88
-
To run the Bicep template, use the following commands from the `aistudio-basics` directory:
88
+
To run the Bicep template, use the following commands from the `aifoundry-basics` directory:
89
89
90
90
1. To create a new Azure Resource Group, use the following command. Replace `exampleRG` with the name of your resource group, and `eastus` with the Azure region to use:
Copy file name to clipboardExpand all lines: articles/ai-foundry/how-to/deploy-nvidia-inference-microservice.md
+6-7Lines changed: 6 additions & 7 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -5,7 +5,7 @@ description: Learn to deploy NVIDIA Inference Microservices, using Azure AI Foun
5
5
manager: scottpolly
6
6
ms.service: azure-ai-foundry
7
7
ms.topic: how-to
8
-
ms.date: 03/14/2024
8
+
ms.date: 03/19/2025
9
9
ms.author: ssalgado
10
10
author: ssalgadodev
11
11
ms.reviewer: tinaem
@@ -16,7 +16,7 @@ ms.custom: devx-track-azurecli
16
16
# How to deploy NVIDIA Inference Microservices
17
17
18
18
In this article, you learn how to deploy NVIDIA Inference Microservices (NIMs) on Managed Compute in the model catalog on Foundry. NVIDIA inference microservices are containers built by NVIDIA for optimized pre-trained and customized AI models serving on NVIDIA GPUs.
19
-
Get improved TCO (total cost of ownership) and performance with NVIDIA NIMs offered for one-click deployment on Foundry, with enterprise production-grade software under NVIDIA AI Enterprise license.
19
+
Get increased throughput and reduced total cost ownership with NVIDIA NIMs offered for one-click deployment on Foundry, with enterprise production-grade software under NVIDIA AI Enterprise license.
@@ -65,12 +65,12 @@ Get improved TCO (total cost of ownership) and performance with NVIDIA NIMs offe
65
65
4. Select the NVIDIA NIM of your choice. In this article, we are using **Llama-3.3-70B-Instruct-NIM-microservice** as an example.
66
66
5. Select **Deploy**.
67
67
6. Select one of the NVIDIA GPU based VM SKUs supported for the NIM, based on your intended workload. You need to have quota in your Azure subscription.
68
-
7. You can then customize your deployment configuration for the instance count, select an existing endpoint or create a new one, etc. For the example in this article, we consider an instance count of **2** and create a new endpoint.
68
+
7. You can then customize your deployment configuration for the instance count, select an existing endpoint or create a new one, etc. For the example in this article, we consider an instance count of **1** and create a new endpoint.
69
69
70
70
:::image type="content" source="../media/how-to/deploy-nvidia-inference-microservice/project-customization.png" alt-text="A screenshot showing project customization options in the deployment wizard." lightbox="../media/how-to/deploy-nvidia-inference-microservice/project-customization.png":::
71
71
72
72
8. Select **Next**
73
-
9. Then, review the pricing breakdown for the NIM deployment, terms of use and license agreement associated with the NIM offer. The pricing breakdown helps to inform what the aggregated pricing for the NIM software deployed would be, which is a function of the number of NVIDIA GPUs in the VM instance that was selected in the previous steps. In addition to the applicable NIM software price, Azure Compute charges also applies based on your deployment configuration.
73
+
9. Then, review the pricing breakdown for the NIM deployment, terms of use and license agreement associated with the NIM offer. The pricing breakdown helps inform what the aggregated pricing for the NIM software deployed would be, which is a function of the number of NVIDIA GPUs in the VM instance that was selected in the previous steps. In addition to the applicable NIM software price, Azure Compute charges also applies based on your deployment configuration.
74
74
75
75
:::image type="content" source="../media/how-to/deploy-nvidia-inference-microservice/payment-description.png" alt-text="A screenshot showing the necessary user payment agreement detailing how the user is charged for deploying the models." lightbox="../media/how-to/deploy-nvidia-inference-microservice/payment-description.png":::
76
76
@@ -84,14 +84,13 @@ NVIDIA NIMs on Foundry expose an OpenAI compatible API, learn more about the pay
84
84
85
85
## Security scanning for NIMs by NVIDIA
86
86
87
+
NVIDIA ensures the security and reliability of NVIDIA NIM container images through best-in-class vulnerability scanning, rigorous patch management, and transparent processes. Learn the details [here](https://docs.nvidia.com/ai-enterprise/planning-resource/security-for-azure-ai-foundry/latest/introduction.html). Microsoft works with NVIDIA to get the latest patches of the NIMs to deliver secure, stable, and reliable production-grade software within AI Foundry.
88
+
Users can refer to the last updated time for the NIM in the model overview page, and you can redeploy to get the latest version of NIM from NVIDIA on Foundry.
87
89
88
90
Redeploy to get the latest version of NIM from NVIDIA on Foundry.
89
91
90
92
## Network Isolation support for NIMs
91
93
92
-
NVIDIA ensures the security and reliability of NVIDIA NIM container images through best-in-class vulnerability scanning, rigorous patch management, and transparent processes. Learn the details [here](https://docs.nvidia.com/ai-enterprise/planning-resource/security-for-azure-ai-foundry/latest/introduction.html). Microsoft works with NVIDIA to get the latest patches of the NIMs to deliver secure, stable, and reliable production-grade software within AI Foundry.
93
-
Users can refer to the last updated time for the NIM in the model overview page, and you can redeploy to get the latest version of NIM from NVIDIA on Foundry.
94
-
95
94
While NIMs are in preview on Foundry, workspaces with Public Network Access disabled will have a limitation of being able to create only one successful deployment in the private workspace or project. Note, there can only be a single active deployment in a private workspace, attempts to create more active deployments will end in failure.
0 commit comments