Installation¶

RBLN SDK provides a runtime binding to the C/C++ language for applications where Python runtime cannot be used or very low latency is required.
The RBLN SDK C/C++ Runtime API is currently available on Debian/Ubuntu OS, and it can be installed via the APT repository by adding the official Rebellions GPG key as shown below:

1. Add Rebellions official GPG key:

   1 2 3 4 5

   $ sudo apt-get update $ sudo apt-get install ca-certificates curl $ sudo install -m 0755 -d /etc/apt/keyrings $ sudo curl -fsSL https://nexus.rebellions.ai/repository/raw-public/rebellions.asc -o /etc/apt/keyrings/rebellions.asc $ sudo chmod a+r /etc/apt/keyrings/rebellions.asc

2. Add the repository to APT sources:

   1 2 3

   $ echo \ "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/rebellions.asc] https://nexus.rebellions.ai/repository/apt-public/ stable main" | \ sudo tee /etc/apt/sources.list.d/rebellions-apt-public.list > /dev/null

3. Update APT repository

   1	$ sudo apt-get update

4. Install the package

   1	$ sudo apt-get install rbln-sdk

Installed files¶

Verify the installation¶

1
2
3

$ dpkg -L rbln-sdk | grep -E 'rbln\.h|librbln_runtime\.so'
/usr/local/include/rbln/rbln.h
/usr/local/lib/librbln_runtime.so

Next steps¶

• Image Classification — compile a PyTorch ResNet50 model in Python and run it with the C/C++ runtime.
• Object Detection — the same flow with a YOLOv8 model and multiple outputs.
• C API — the full function reference.