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
@@ -23,24 +23,24 @@ import Requirements from '@macros/iam/requirements.mdx'
23
23
Scaleway Managed Inference allows you to deploy various AI models, either from the Scaleway catalog or by importing a custom model. For detailed information about supported models, visit our [Supported models in Managed Inference](/managed-inference/reference-content/supported-models/) documentation.
24
24
</Message>
25
25
<Messagetype="note">
26
-
Some models may require acceptance of an end-user license agreement. If prompted, review the terms and conditions and accept the license accordingly.
26
+
Some models may require acceptance of an end-user license agreement (EULA). If prompted, review the terms and conditions and accept the license accordingly.
27
27
</Message>
28
28
- Choose the geographical **region** for the deployment.
29
29
- For custom models: Choose the model quantization.
30
30
<Messagetype="tip">
31
31
Each model comes with a default quantization. Select lower bits quantization to improve performance and enable the model to run on smaller GPU nodes, while potentially reducing precision.
32
32
</Message>
33
-
-Specify the GPU Instance type to be used with your deployment.
34
-
5. Choose the number of nodes for your deployment. Note that this feature is currently in [Public Beta](https://www.scaleway.com/betas/).
35
-
<Messagetype="note">
36
-
High availability is only guaranteed with two or more nodes.
37
-
</Message>
38
-
6. Enter a **name** for the deployment, and optional tags.
39
-
7. Configure the **network connectivity** settings for the deployment:
33
+
-Select a node type, the GPU Instance that will be used with your deployment.
34
+
- Choose the number of nodes for your deployment. Note that this feature is currently in [Public Beta](https://www.scaleway.com/betas/).
35
+
<Messagetype="tip">
36
+
High availability is only guaranteed with two or more nodes.
37
+
</Message>
38
+
5. Enter a **name** for the deployment, and optional tags.
39
+
6. Configure the **network connectivity** settings for the deployment:
40
40
- Attach to a **Private Network** for secure communication and restricted availability. Choose an existing Private Network from the drop-down list, or create a new one.
41
41
- Set up **Public connectivity** to access resources via the public internet. Authentication by API key is enabled by default.
42
42
<Messagetype="important">
43
43
- Enabling both private and public connectivity will result in two distinct endpoints (public and private) for your deployment.
44
44
- Deployments must have at least one endpoint, either public or private.
45
45
</Message>
46
-
8. Click **Deploy model** to launch the deployment process. Once the model is ready, it will be listed among your deployments.
46
+
7. Click **Deploy model** to launch the deployment process. Once the model is ready, it will be listed among your deployments.
Once you have finished your inference tasks you can delete your deployment. This page explains how to do so from the Scaleway console.
14
+
Once you have finished your inference tasks, you can delete your deployment. This page explains how to do so from the Scaleway console.
15
15
16
16
<Requirements />
17
17
@@ -21,11 +21,13 @@ Once you have finished your inference tasks you can delete your deployment. This
21
21
22
22
1. Click **Managed Inference** in the **AI** section of the [Scaleway console](https://console.scaleway.com) side menu. A list of your deployments displays.
23
23
2. From the drop-down menu, select the geographical region you want to manage.
24
-
3. Choose a deployment either by clicking its name or selecting **More info** from the drop-down menu represented by the icon <Iconname="more" /> to access the deployment dashboard.
25
-
4. Click the **Settings** tab of your deployment to display additional settings.
26
-
5. Click **Delete deployment**.
27
-
6. Type **DELETE** to confirm and click **Delete deployment** to delete your deployment.
24
+
3. Choose a deployment by clicking its name. The deployment's **Overview** page displays.
25
+
4. Navigate to the **Settings** tab.
26
+
5. Click **Delete deployment** at the bottom of the page.
27
+
6. Type **DELETE** to confirm and click **Delete deployment**.
28
+
29
+
Alternatively, from the Deployments listing, click the <Iconname="more" /> icon next to the deployment name you no longer need, and click **Delete**. A pop-up appears. Type **DELETE** to confirm, then click **Delete deployment**.
28
30
29
31
<Messagetype="important">
30
-
Deleting a deployment is a permanent action and will erase all its associated data.
32
+
Deleting a deployment is a permanent action that erases all its associated data and resources.
description: Start with Scaleway Managed Inference for secure, scalable AI model deployment in Europe's premier platform. Privacy-focused, fully managed.
4
4
tags:
5
5
dates:
6
-
validation: 2025-02-24
6
+
validation: 2025-07-21
7
7
categories:
8
8
- ai-data
9
9
---
@@ -22,6 +22,11 @@ Here are some of the key features of Scaleway Managed Inference:
22
22
***Complete data privacy**: [No storage](/managed-inference/reference-content/data-privacy-security-scaleway-ai-services/#data-storage-policies) or third-party access to your data (prompt or responses), to ensure it remains exclusively yours.
23
23
***Interoperability**: Scaleway Managed Inference was designed as a drop-in [replacement for the OpenAI APIs](/managed-inference/reference-content/openai-compatibility/), for a seamless transition on your applications already using its libraries.
24
24
25
+
## Console overview
26
+
27
+
Discover the Managed Inference interface on the Scaleway console.
- A Scaleway account logged into the [console](https://console.scaleway.com)
@@ -38,11 +43,14 @@ Here are some of the key features of Scaleway Managed Inference:
38
43
Scaleway Managed Inference allows you to deploy various AI models, either from the Scaleway catalog or by importing a custom model. For detailed information about supported models, visit our [Supported models in Managed Inference](/managed-inference/reference-content/supported-models/) documentation.
39
44
</Message>
40
45
<Messagetype="note">
41
-
Some models may require acceptance of an end-user license agreement. If prompted, review the terms and conditions and accept the license accordingly.
46
+
Some models may require acceptance of an end-user license agreement (EULA). If prompted, review the terms and conditions and accept the license accordingly.
42
47
</Message>
43
48
- Choose the geographical **region** for the deployment.
44
-
-Specify the GPU Instance type to be used with your deployment.
49
+
-Select a node type, the GPU Instance that will be used with your deployment.
45
50
- Choose the number of nodes for your deployment. Note that this feature is currently in [Public Beta](https://www.scaleway.com/betas/).
51
+
<Messagetype="note">
52
+
High availability is only guaranteed with two or more nodes.
53
+
</Message>
46
54
5. Enter a **name** for the deployment, along with optional tags to aid in organization.
47
55
6. Configure the **network** settings for the deployment:
48
56
- Enable **Private Network** for secure communication and restricted availability within Private Networks. Choose an existing Private Network from the drop-down list, or create a new one.
@@ -59,9 +67,10 @@ Managed Inference deployments have authentication enabled by default. As such, y
59
67
60
68
1. Click **Managed Inference** in the **AI** section of the side menu. The Managed Inference dashboard displays.
61
69
2. From the drop-down menu, select the geographical region where you want to manage.
62
-
3. Click <Iconname="more" /> next to the deployment you want to edit. The deployment dashboard displays.
63
-
4.Click **Generate key** in the **Deployment connection** section of the dashboard. The token creation wizard displays.
70
+
3. Click the name of the deployment you wish to access. The deployment's **Overview** page displays.
71
+
4.Scroll down to the **Deployment authentication** section and click the **Generate key** button. The token creation wizard displays.
64
72
5. Fill in the [required information for API key creation](/iam/how-to/create-api-keys/) and click **Generate API key**.
73
+
6. Copy and safely store your credentials before closing the window, as they will not be shown again.
65
74
66
75
<Messagetype="tip">
67
76
You have full control over authentication from the **Security** tab of your deployment. Authentication is enabled by default.
@@ -70,9 +79,9 @@ Managed Inference deployments have authentication enabled by default. As such, y
70
79
## How to interact with Managed Inference
71
80
72
81
1. Click **Managed Inference** in the **AI** section of the side menu. The Managed Inference dashboard displays.
73
-
2. From the drop-down menu, select the geographical region where you want to manage.
74
-
3. Click <Iconname="more" /> next to the deployment you want to edit. The deployment dashboard displays.
75
-
4. Click the **Inference** tab. Code examples in various environments display. Copy and paste them into your code editor or terminal.
82
+
2. From the drop-down menu, select the geographical region where your desired deployment was created.
83
+
3. Click the name of the deployment you wish to edit. The deployment's **Overview** page displays.
84
+
4. Click the **Playground** tab, then **View code** to see code examples in various environments. Copy and paste them into your code editor or terminal.
76
85
77
86
<Messagetype="note">
78
87
Prompt structure may vary from one model to another. Refer to the specific instructions for use in our [dedicated documentation](/managed-inference/reference-content/).
@@ -81,12 +90,14 @@ Managed Inference deployments have authentication enabled by default. As such, y
81
90
## How to delete a deployment
82
91
83
92
1. Click **Managed Inference** in the **AI** section of the [Scaleway console](https://console.scaleway.com) side menu. A list of your deployments displays.
84
-
2. From the drop-down menu, select the geographical region where you want to create your deployment.
85
-
3. Choose a deployment either by clicking its name or selecting **More info** from the drop-down menu represented by the icon <Iconname="more" /> to access the deployment dashboard.
86
-
4. Click the **Settings** tab of your deployment to display additional settings.
87
-
5. Click **Delete deployment**.
88
-
6. Type **DELETE** to confirm and click **Delete deployment** to delete your deployment.
93
+
2. From the drop-down menu, select the geographical region where your deployment was created.
94
+
3. Click the name of the deployment you wish to delete.
95
+
4. Navigate to the **Settings** tab.
96
+
5. Click **Delete deployment** at the bottom of the page.
97
+
6. Type **DELETE** to confirm and click **Delete deployment**.
98
+
99
+
Alternatively, from the Deployments listing, click the <Iconname="more" /> icon next to the deployment name you no longer need, and click **Delete**. A pop-up appears. Type **DELETE** to confirm, then click **Delete deployment**.
89
100
90
101
<Messagetype="important">
91
-
Deleting a deployment is a permanent action, and will erase all its associated configuration and resources.
102
+
Deleting a deployment is a permanent action that erases all its associated data and resources.
0 commit comments