From cd5a46578d819474e9772ea7f83b982c1ce66ef6 Mon Sep 17 00:00:00 2001
From: David Jurado <david.jurado@factored.ai>
Date: Tue, 25 Nov 2025 17:09:34 -0500
Subject: [PATCH 1/2] update docs

---
 docs/minified-benchmarks/automotive.md   | 72 ++++++++++++++++++++++++
 docs/minified-benchmarks/introduction.md |  1 +
 2 files changed, 73 insertions(+)
 create mode 100644 docs/minified-benchmarks/automotive.md

diff --git a/docs/minified-benchmarks/automotive.md b/docs/minified-benchmarks/automotive.md
new file mode 100644
index 0000000..4680e38
--- /dev/null
+++ b/docs/minified-benchmarks/automotive.md
@@ -0,0 +1,72 @@
+# Automotive - BEVFormer
+
+The benchmark reference for BEVFormer can be found in this [link](https://github.com/mlcommons/mlperf_automotive/tree/master/automotive/camera-3d-detection), and here is the PR for the minified benchmark implementation: [link](https://github.com/mlcommons/mlperf_automotive/pull/87).
+
+## Project setup
+
+An important requirement is that you must have Docker installed.
+
+```bash
+# Create Python environment and install MLCube Docker runner 
+virtualenv -p python3 ./env && source ./env/bin/activate && pip install pip==24.0 && pip install mlcube-docker
+# Fetch the implementation from GitHub
+git clone https://github.com/mlcommons/mlperf_automotive && cd ./mlperf_automotive
+git fetch origin pull/87/head:feature/mlcube_bevformer && git checkout feature/mlcube_bevformer
+cd ./automotive/camera-3d-detection/mlcube
+```
+
+Inside the mlcube directory run the following command to check implemented tasks.
+
+```shell
+mlcube describe
+```
+
+###  Extra requirements
+
+You need to run these steps locally.
+
+```shell
+pip install mlc-scripts
+```
+
+Then run this command and follow the instructions.
+
+```shell
+mlcr get,bevformer,_mlc,_rclone
+```
+
+After this you will have a new configuration at `~/.config/rclone/rclone.conf`.
+
+Finally you just need to copy that file into the `workpace` folder.
+
+```shell
+cp ~/.config/rclone/rclone.conf workspace
+```
+
+### MLCube tasks
+
+* Demo tasks:
+
+Download demo dataset and models.
+
+```shell
+mlcube run --task=download_demo -Pdocker.build_strategy=always
+```
+
+Train demo.
+
+```shell
+mlcube run --task=demo -Pdocker.build_strategy=always
+```
+
+### Execute the complete pipeline
+
+You can execute the complete pipeline with one single command.
+
+* Demo pipeline:
+
+```shell
+mlcube run --task=download_demo,demo -Pdocker.build_strategy=always
+```
+
+**Note**: To rebuild the image use the flag: `-Pdocker.build_strategy=always` during the `mlcube run` command.
diff --git a/docs/minified-benchmarks/introduction.md b/docs/minified-benchmarks/introduction.md
index 3b24045..c69ff5d 100644
--- a/docs/minified-benchmarks/introduction.md
+++ b/docs/minified-benchmarks/introduction.md
@@ -19,3 +19,4 @@ The main advantages of these minified benchmarks are:
 - [Bert](bert.md)
 - [Object Detection](object-detection.md)
 - [Graph Neural Network](gnn.md)
+- [Automotive - BEVFormer](automotive.md)

From 46dedf3088ce38acf965f2f0fa74837ab5891c65 Mon Sep 17 00:00:00 2001
From: David Jurado <david.jurado@factored.ai>
Date: Tue, 25 Nov 2025 17:12:08 -0500
Subject: [PATCH 2/2] update docs

---
 mkdocs.yml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mkdocs.yml b/mkdocs.yml
index c455b4b..8422536 100644
--- a/mkdocs.yml
+++ b/mkdocs.yml
@@ -35,6 +35,7 @@ nav:
     - Bert: minified-benchmarks/bert.md
     - Object Detection: minified-benchmarks/object-detection.md
     - Graph Neural Network: minified-benchmarks/gnn.md
+    - Automotive - BEVFormer: minified-benchmarks/automotive.md
 
 theme:
   features: