feat(ai): byom (#4726)

* feat(ai): byom

* feat(ai): add note

* feat(ai): fix doc

* Update pages/managed-inference/how-to/import-custom-model.mdx

Co-authored-by: Jessica <[email protected]>

---------

Co-authored-by: Jessica <[email protected]>

Author: bene2k1

Diff for: menu/navigation.json

@@ -820,6 +820,10 @@
                     "label": "Deploy a model",
                     "slug": "create-deployment"
                   },
+                  {
+                    "label": "Import a custom model",
+                    "slug": "import-custom-model"
+                  },
                   {
                     "label": "Monitor a deployment",
                     "slug": "monitor-deployment"

Diff for: pages/managed-inference/how-to/import-custom-model.mdx

@@ -0,0 +1,48 @@
+---
+meta:
+  title: How to import custom models into Managed Inference
+  description: Learn how to import your custom models into Scaleway's Managed Inference platform.
+content:
+  h1: How to import custom models into Managed Inference
+  paragraph: Learn how to import your custom models into Scaleway's Managed Inference platform.
+tags: managed-inference ai-data import custom model
+dates:
+  validation: 2025-03-27
+  posted: 2025-03-27
+categories:
+  - ai-data
+---
+
+Scaleway provides a selection of common models for deployment from the Scaleway console. If you need a specific model, you can import it into Managed Inference directly from Hugging Face or a Scaleway Object Storage bucket.
+
+<Message type="note">
+  This feature is currently in **beta stage** and will evolve in the future.
+</Message>
+
+<Macro id="requirements" />
+- A Scaleway account logged into the [console](https://console.scaleway.com).  
+- [Owner](/identity-and-access-management/iam/concepts/#owner) status or [IAM permissions](/identity-and-access-management/iam/concepts/#permission) to perform actions in your Organization.
+
+1. Click **Managed Inference** in the **AI & Data** section of the side menu in the [Scaleway console](https://console.scaleway.com/) to access the dashboard.
+2. Click **Deploy a model** to launch the model deployment wizard.
+3. In the **Choose a model** section, select **Custom model**. If you have no model yet, click **Import a model** to start the model import wizard.
+4. Choose an upload source:
+   - **Hugging Face**: Pull the model from Hugging Face.
+   - **Object Storage**: This feature is coming soon.
+5. Enter your Hugging Face access token, which must have READ access to the repository.
+    <Message type="note">
+      [Learn how to generate a Hugging Face access token](https://huggingface.co/docs/hub/security-tokens).
+    </Message>
+6. Enter the name of the Hugging Face repository to pull the model from.
+    <Message type="note">
+      Ensure you have access to gated models if applicable. Refer to the [Hugging Face documentation](https://huggingface.co/docs/hub/en/models-gated) for details.
+    </Message>
+7. Choose a name for your model. The name must be unique within your Organization and Project and cannot be changed later.
+8. Click **Verify import** to check your Hugging Face credentials and ensure model compatibility.
+9. Review the summary of your import, which includes:
+    - Context size by node type.
+    - Quantization options.
+    - Estimated cost.
+   Once checked, click **Begin import** to finalize the process.
+
+Your imported model will now appear in the model library. You can proceed to [deploy your model on Managed Inference](/ai-data/managed-inference/how-to/create-deployment/).