From 7f62b418a4c605257183c3bbf1f7b98f0904fe5f Mon Sep 17 00:00:00 2001
From: Ettore Di Giacinto <mudler@localai.io>
Date: Wed, 29 Jan 2025 15:16:07 +0100
Subject: [PATCH] chore(docs): add documentation for l4t images
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---
.../docs/getting-started/container-images.md | 14 +++++++++++++-
docs/content/docs/reference/nvidia-l4t.md | 10 ++++++++--
2 files changed, 21 insertions(+), 3 deletions(-)
diff --git a/docs/content/docs/getting-started/container-images.md b/docs/content/docs/getting-started/container-images.md
index 64f6dbc93165..a6a955adbcf0 100644
--- a/docs/content/docs/getting-started/container-images.md
+++ b/docs/content/docs/getting-started/container-images.md
@@ -154,7 +154,7 @@ Images are available with and without python dependencies. Note that images with
Images with `core` in the tag are smaller and do not contain any python dependencies.
-{{< tabs tabTotal="7" >}}
+{{< tabs tabTotal="8" >}}
{{% tab tabName="Vanilla / CPU Images" %}}
| Description | Quay | Docker Hub |
@@ -236,6 +236,18 @@ Images with `core` in the tag are smaller and do not contain any python dependen
| Versioned image including FFMpeg, no python | `quay.io/go-skynet/local-ai:{{< version >}}-vulkan-fmpeg-core` | `localai/localai:{{< version >}}-vulkan-fmpeg-core` |
{{% /tab %}}
+{{% tab tabName="Nvidia Linux for tegra" %}}
+
+These images are compatible with Nvidia ARM64 devices, such as the Jetson Nano, Jetson Xavier NX, and Jetson AGX Xavier. For more information, see the [Nvidia L4T guide]({{%relref "docs/reference/nvidia-l4t" %}}).
+
+| Description | Quay | Docker Hub |
+| --- | --- |-------------------------------------------------------------|
+| Latest images from the branch (development) | `quay.io/go-skynet/local-ai:master-nvidia-l4t-arm64-core` | `localai/localai:master-nvidia-l4t-arm64-core` |
+| Latest tag | `quay.io/go-skynet/local-ai:latest-nvidia-l4t-arm64-core` | `localai/localai:latest-nvidia-l4t-arm64-core` |
+| Versioned image | `quay.io/go-skynet/local-ai:{{< version >}}-nvidia-l4t-arm64-core` | `localai/localai:{{< version >}}-nvidia-l4t-arm64-core` |
+
+{{% /tab %}}
+
{{< /tabs >}}
## See Also
diff --git a/docs/content/docs/reference/nvidia-l4t.md b/docs/content/docs/reference/nvidia-l4t.md
index 028ee5318fef..ce0fd5e95c6f 100644
--- a/docs/content/docs/reference/nvidia-l4t.md
+++ b/docs/content/docs/reference/nvidia-l4t.md
@@ -21,7 +21,13 @@ git clone https://github.com/mudler/LocalAI
cd LocalAI
-docker build --build-arg SKIP_DRIVERS=true --build-arg BUILD_TYPE=cublas --build-arg BASE_IMAGE=nvcr.io/nvidia/l4t-jetpack:r36.4.0 --build-arg IMAGE_TYPE=core -t localai-orin .
+docker build --build-arg SKIP_DRIVERS=true --build-arg BUILD_TYPE=cublas --build-arg BASE_IMAGE=nvcr.io/nvidia/l4t-jetpack:r36.4.0 --build-arg IMAGE_TYPE=core -t quay.io/go-skynet/local-ai:master-nvidia-l4t-arm64-core .
+```
+
+Otherwise images are available on quay.io and dockerhub:
+
+```bash
+docker pull quay.io/go-skynet/local-ai:master-nvidia-l4t-arm64-core
```
## Usage
@@ -29,7 +35,7 @@ docker build --build-arg SKIP_DRIVERS=true --build-arg BUILD_TYPE=cublas --build
Run the LocalAI container on Nvidia ARM64 devices using the following command, where `/data/models` is the directory containing the models:
```bash
-docker run -e DEBUG=true -p 8080:8080 -v /data/models:/build/models -ti --restart=always --name local-ai --runtime nvidia --gpus all localai-orin
+docker run -e DEBUG=true -p 8080:8080 -v /data/models:/build/models -ti --restart=always --name local-ai --runtime nvidia --gpus all quay.io/go-skynet/local-ai:master-nvidia-l4t-arm64-core
```
Note: `/data/models` is the directory containing the models. You can replace it with the directory containing your models.