Comment on page
Scailable supported devices
With Scailable we make creating and managing highly performant edge AI solutions as easy as possible. To ensure the efficiency of our full edge AI pipline (i.e., from grabbing the camera images and pre-processing, to model inference and output post-processing) we focus on a carefully selected set of edge device. For each of the devices we support we provide extremely efficient, low-level integrations of our AI manager. This often includes automatically using the hardware acceleration (GPU, NPU, TPU) that is available on the device.
In this section of our documentation we first detail our generic one-line install that will work for virtually any linux based device. Next, we list specific OEMs that we partner with and whose devices we support. In the OEM specific pages you will find specific information regarding supported devices from different partners including purchase options.
It is possible to install the AI manager on virtually any Linux based device using our simple one-line install script.
Login to the Edge device and open a shell. Next, type the following command:
sudo bash -ic "$(wget -q -O - https://get.sclbl.net)"
If you have issues with this command due to
wgetnot behaving as expected, the following command offers a
sudo bash -ic "$(curl -fsSL https://get.sclbl.net)"
This will install the Scailable AI manager on the device and should work for ARM32, ARM64 and Intel x86_64 CPU based devices. Note that the installation will also automatically detect the presence of NVIDIA accelerator hardware and will install all the necessary drivers.
After the installation script has run you will see the following message:
Similar to the one-line install above, but this will automatically register the device to your organisation.
sudo bash -ic "$(wget -q -O - https://get.sclbl.net)" autoregister --key <key>
The following table lists all the devices (or device classes) we currently actively support (meaning we extensively test our pipeline on these devices and actively benchmark our library model's performance on these devices). It also means we have active relationships with the manufacturers to provide support and ensure the successful realization of edge AI projects.
We support the following chipsets/accelerators: