I recently decided to have some fun with my Raspberry Pi 5 by adding a Lanner Falcon-H8. My version of the Falcon-H8 has four Hailo-8 AI accelerators providing a total of 104 TOPS. To make this work, I used a Raspberry Pi HAT from Pineboards.
Here’s an image of my setup (without the heatsink):
As you can see, the Raspberry Pi 5 is connected to the Falcon-H8 PCIe card via the Pineboards HAT. The HAT makes it easy to integrate the PCIe card with the Raspberry Pi because the PCIe slot is open-ended and has a separate power connector, so it will not fry your Pi. I used a 12V 5A power supply with a barrel jack connector.
I have been running multiple instances of the applications from our Hailo RPi 5 Example repository.
Here’s an image of two Object Detection and two Pose Estimation examples in action:
You can see the four devices in the HailoRT CLI Monitor.
While this setup is primarily for fun and experimentation, it showcases the potential of using Lanner’s Falcon PCIe cards in more powerful systems. If you’re interested in running multiple AI tasks on many camera streams, you might want to check out the Falcon family of PCIe cards.
The Falcon-H8 accommodates 4, 5, or 6 Hailo-8 AI processors and a PCIe switch.
Feel free to follow the links to learn more about these products and how they might fit into your projects. If you have any questions or need further details, don’t hesitate to ask.
As you can see from the image the module has a external DDR memory on board. The memory will allow the Hailo-10H to run LLMs which are much larger than CNNs locally on the module without stressing the PCIe interface to the host.
The Hailo-10H is currently not yet generally available. We are working on the software support to ensure we provide a complete solution.
Hi @KlausK This looks very interesting. We have been looking for a way to run our custom models on multiple Hailo8Ls using a raspberry Pi 5. We have converted the models and can successfully run the pipeline on a raspberry pi AI Hat+ and now want to improve performance by paralyzing execution across multiple Hailo devices.
Will we be able to use one of the raspberry PCI expansion boards, for example this quad board.? This one also allows use of an external power supply and is more compact than Lanner setup. Do you know if multiple Hailo8L’s can be used with this board? Are there any general restrictions with using multiple Hailo8L on a raspberry pi 5?
@KlausK Is there already an “eta” for 10H? I have already been in contact with Hailo’s German sales partner, but there are no concrete answers yet. And of course no (estimated) price. Can you shed some light?
You can give it a try. It looks like the board has a PCIe gen 2 switch which will limit the PCIe bandwidth, which is already limited by having only one PCIe lane on the Raspberry Pi 5.
As said above the PCIe bandwidth is limited. At some point you will not get higher FPS with more devices because you cannot send data fast enough.
That depends on the network and AI task type. This setup is very limited in PCIe bandwidth due to the single PCIe lane available on the Raspberry Pi.
In my case I just run 4 independent applications. Each app uses a single Hailo-8 device. Generally the HailoRT scheduler will help you run the different tasks and manage devices. You can find more information in the HailoRT User guide.
I’m following up on my February inquiry about the Hailo-10H accelerator module. I had reached out to Hailo’s German sales partner at that time, but I still haven’t received any concrete details. As I’m currently planning several edge computing projects, I’m very interested in learning if there have been any updates—particularly regarding a potential release date, the current status of the software support, or any pricing insights that might be available.
Any information you can share would really help me move forward with my plans.
Thanks for your time and assistance!
Best regards,
Walter
By the way, if you have any insights on how the integration challenges with such advanced technologies might affect other edge computing or generative AI projects, I’d love to hear your thoughts as well.