AI Lounge

👋 Hello Axelera AI Community,My name is Saravanan, and I’m an AI Architect and Executive Officer at Super Quantum AI, based in Gobi, Tamil Nadu, India.I focus on designing advanced AI architectures, multi-agent systems, and next-generation intelligent platforms. My work is centered on building scalable AI infrastructure, intelligent automation, and future-ready AI ecosystems.I’m excited to be part of this community to learn, share knowledge, and connect with fellow AI engineers, researchers, and innovators.You can learn more about me / my work here:• https://saravananai.online• https://eshmoai.onlineLooking forward to meaningful discussions and collaboration.Thank you!— Saravanan

Hey everyone,Excited to share a brand-new video I put together for anyone getting started with the Metis card and Voyager SDK. Whether you're setting up your eval kit or just curious about how inference works on Metis, this walkthrough is for you.🛠️ What’s inside:Setting up your environment and verifying camera input Running YOLOv5s-v7-COCO on a live camera stream Using download_prebuilt for faster setup Running inference on media files and datasets Benchmarking performance Measuring accuracy with mAP and more📺 You can find this tutorial, and more, on our YouTube ChannelThis guide is based on SDK version 1.2.5 and follows the official

Many of you guys have been on the ride since we opened up here (even before), so I thought I’d share a heads-up that Axelera has announced a new funding round of over $250 million! That takes total funding to over $450 million since the company was founded in 2021, and is apparently the largest investment ever in an EU AI semiconductor company. 😮The funding will go towards scaling manufacturing, expanding the partner network, and developing the SDK further, so good news for everyone here building on the platform! Thanks for being here with us!Check out more of the details here.

If you've wanted to peek under the hood of how your Metis hardware talks to Linux, there’s a new Axelera AI repo with the PCIe driver source code.Repo: https://github.com/axelera-ai-hub/axelera-driverFor most of us running the standard Voyager SDK setup, you won't likely need to touch this. The driver gets installed automatically. But if you're doing something a bit more adventurous (custom kernel builds, embedded systems, that sort of thing) this could be really useful. I know at least a few people on here have been experimenting with Debian and Yocto, for instance.Quick overview of what's there:It's the metis.ko kernel module. The one that handles all the PCIe communication between your system and the Metis hardware. Currently it supports Ubuntu 22.04 and 24.04 (LTS).Building it yourself is pretty

Hello Axelera Community!My name is Ioannis and I am a part-time working student here. Before moving to the Netherlands to start my Master's studies, I was researching potential companies to intern with, and Axelera was a name that really stood out. When I attended a presentation by the company during my Master's kick-off events and heard they were looking for working students, it felt like the perfect opportunity!I officially joined in December and have been working with the Metis AIPU on the Lenovo P3 Tiny and an OrangePI since then. Over the last couple of months, I have worked on a variety of scenarios, starting from simply deploying models to building a mini demo that combines Whisper, LLaMA, and a text-to-speech model. I have also been documenting my experience along the way, testing the Voyager SDK documentation and evaluating how intuitive and user-friendly it feels for a newcomer.When it came to learning the new hardware and software, the guides were ver

Hi Axelera inferences and compiler available https://hub.degirum.com

Hello everyone,Abdi here. I am a part-time working student at Axelera. I joined in December.I am having a blast playing with the Metis devices. Our task is focused on testing the Voyager SDK documentation. Is it clear enough for the customer? Where can it be improved? We test the documentation by actually following it, such as working through the tutorials provided in the documentation.Furthermore, we test how easy it is to perform tasks that users may actually want to do, such as counting how many objects are in a video frame using YOLO. Deploying models,running different kinds of models.We evaluate how useful the documentation is in this context and identify where the gaps are.Currently, I am working on integrating an external tool, Whisper, with the Metis Dev System on the Arduino Portenta X8, and  routing Whisper’s output into an LLM running on the device. -Abdi   

I’m interested in hearing from everyone here about which models you’re successfully using with your Metis device and Voyager SDK, and which ones you’d like to see being officially supported.This could be really useful info in terms of prioritisation when it comes to adding more support in the model zoo.

Hi everyone!This is my first post in the community, so let me introduce myself! My name is Pablo and I’m new to Axelera, joined in December as a part-time working student.Throughout these last two months I’ve been using the Metis AIPU both in a Raspberry Pi 5 and with the Advantech MIC-770, running through several use cases and analyzing documentation and user experience. I started with the most basic setup tasks before making my way to all Voyager SDK’s tutorials and examples/demos, and even experimented with combining external tools like Whisper into the system’s LLMs. It’s indeed quite fun and impressive to see what Metis is capable of! (and having such interesting projects on the community clearly proves that 😄)By acting as a sort of customer that is playing with a new system, I hope that my perspective is relatable and helps Axelera to keep improving. I have to say I’m very happy with how my experience is going so far, and can’t help but feel more excited a

Hi Axelera community,I’ve just started working with the Metis SBC and Voyager SDK, and I’m looking for some structured guidance on how to get up to speed.My background:~10 years of hardware experience (board-level design, complex FPGA design using VHDL/Verilog) Comfortable with Python and have worked with AI models at an academic level Limited embedded experience beyond bare-metal concepts (I’ve usually worked alongside dedicated embedded engineers)I’d love suggestions on: A learning path for Metis + Voyager SDK Where to start (simple “hello world”–style projects) How to progress toward more complex designs (e.g., integrating peripherals, using accelerators, optimizing performance, etc.) Career/skills development advice For those who have followed a similar path, from low-level hardware/FPGA work into higher-level embedded Linux and SoC-based systems:

Hi everyone,Has anyone here collaborated with remotely hired AI or edge AI engineers on Axelera Metis or Voyager SDK projects, for example, through a remote recruitment agency like CrewBloom?I’d love to hear how you handled onboarding, access to hardware, SDK setup, and day-to-day collaboration in a fully remote setup. Any lessons learned or tips that helped projects run smoothly would be greatly appreciated.

The NanoPC-T6 from FriendlyElec is now supported by Voyager SDK. This is one that's been requested a few times (shout out to the folks who’ve previously asked for it), so I figured it was worth a proper write-up.What's the NanoPC-T6?It's an RK3588-based SBC that's been popular in the community for a while, particularly for networking and NAS builds. The board itself is pretty compact and comes with dual 2.5GbE ports, an M.2 slot for NVMe storage, and somewhat unusually for an SBC, an HDMI input alongside the outputs. Pricing starts around $100 for the 4GB/32GB variant and goes up to about $150 for the 16GB/256GB version. So it’s an affordable piece of kit and a smart choice for the right projects.

hi there,i am currently writing up an application with friends for a grant on “ai&art” which is due by tomorrow.we want to do music reactive visuals on edge with multimodal inputs and want to use the Metis for live inference. i think of visuals being an interesting playground since they allow to very freely construct the loads for the chip. if you are interested in collaborating please feel free to reach out! there is no requirement on expertise.  ideas only are also very much welcome.(as well as additional sources for funding or sponsors)hope to have caught your interestbest carlo 

Red Dwarf’s really well known for how well it predicted (albeit comedicaly) VR tech, but it did a lot more than that. It heralded a lot of advance in AI that we’re now actually seeing emerge: conversational appliances, narcissistic holograms, forgetful mainframes, and borderline neurotic robot butlers not being the least of them.25th November = Gazpacho Soup Day. Look it up.The show was set in the 22nd Century, but it’s only 2025 and it’s already coming true. With edge AI powering robotics, smart devices, and real-time vision on the edge, so many of those hilarious sci-fi predictions are fast becoming reality. From Rimmer's hologram (an early take on digital consciousness) to Kryten's helpful, protocol-bound persona (think domestic service robotics with a strong opinion on laundry), Red Dwarf imagined AI not just as

Have you seen that ​@Victor Labian’s successfully brought up the Voyager SDK on the Orange Pi 5 Plus with a Metis M.2 module? It took a bit of work—Ubuntu flashing, driver rebuilds, and tweaking the PCIe device tree—but it’s running, and it’s fast. 😃This setup is seriously impressive for something so compact and affordable. Inference runs smoothly, and with some tuning, it could potentially be running advanced models like YOLOv8 without trouble.It’s just an experiment and a test at this point. No big plans around the Orange Pi, but it looks like a really promising start.If you’re experimenting with AI on SBCs—or thinking about it—I’d love to hear what you’re working on. Orange Pi, Raspberry Pi, custom boards, anything edge. 👍

All the release notes for Voyager updates go straight out on the GitHub repo, so I don’t tend to parrot them here, but this is a pretty big one and feels like it deserves a spot here on the community!If you’ve been using 1.3 already, there are some nice changes that make life easier.A few things that particularlt stand out to me:🔹 Cascade pipelines feel smoother. Chaining models together (like running a classifier on detections) takes less fiddling around than before. 🔹 More operator and metadata options. You can now shape pre/post-processing and inference results in ways that fit better with your own app. 🔹 Model Zoo is easier to adapt. Swapping in your own weights on the reference pipelines is less hassle, so you can get something tuned to your dataset faster. 🔹 Custom evaluators are handy if you want accuracy measured in a way that matches your own project rath

Dear Axelera Team, We are Master’s students in Business Engineering: Technology and Entrepreneurship at KU Leuven. As part of our course on Strategic Management of Technology, we are exploring how innovative companies manage and foster innovation. Through Axelera’s LinkedIn we noticed your commitment to supporting innovative ideas. We would be very interested in learning more about your approach to innovation management. Our project would involve studying your innovation practices and providing an analytical report as an outcome. Would you be open to collaborating with us on this project? Thank you very much for your time and consideration. Best regards,Anna VellaKU Leuven – Faculty of Economics and BusinessLeuven, Belgium 

Buongiorno a tutti, Mi chiamo Vito e sono il titolare di una società Italiana, una start-up. Insegno anche in un istituto tecnico di Brescia Robotica, Elettronica e Informatica. Abbiamo avviato un progetto per la realizzazione di un robot umanoide nella mia società con alcuni dei miei studenti, qualche mese fa nell'ambito dell'assistenza. Ho visto l'intervista dell'Ing. Del Maffeo e sono rimasto colpito. Spanner, ​@Spanner dobbiamo implementare il robot con AI e quindi di una scheda potente, possiamo collaborare? Il potenziale è grande..  come potremmo approfondire l'argomento? Vi ringrazio a tutti in anticipo.. 

Thought you might want to check out the live stream from YOLO Vision that’s happening today in London. Some of the Axelera AI team are there, and will be up on stage soon! 

Hello,I am currently running performance tests on the Metis M.2 card with different models (e.g., YOLOv8n).I observed a behavior that I would like to clarify: When running with 1 AIPU core, I get lower latency and the same FPS as when using multiple cores (4). However, with 4 AIPU cores, the latency per image is higher, even though the FPS does not increase. In addition, CPU utilization is noticeably higher with 4 cores (around 17%) compared to only ~0.8% with 1 core. I would like to know: Is this expected behavior (due to synchronization overhead between AIPU cores)? Is there a recommended configuration to optimize either latency or throughput (FPS) depending on the use case? Is it normal that CPU usage increases significantly when using 4 cores, given

In case anyone on here hasn’t spotted it in the wild yet, the Metis M.2 Max was just announced. It’s basically managed to pack PCIe card-level performance into an M.2 stick. So that’s better performance for LLMs and vision transformers on much smaller host devices (RPi, Orange Pi, etc), all while keeping power draw super low (around 6.5W). It’s been bumped up to 16GB of memory, slimmer design options, and added security features for tougher environments.Feels like a big step forward for anyone wanting to run GenAI, computer vision, or LLM workloads locally, on devices with an impressively small footprint, without needing a data centre to do it 😆.Shipping starts later this year.

Heads-up if you’re building a new AI project from scratch – the new Metis Compute Board is now up for pre-order!It’s a compact SBC with the Metis AI accelerator baked right in, powered by the ARM-based RK3588. And it runs the Voyager SDK out of the box. Loads of interfaces, solid memory specs, tiny footprint (170x170mm), and very dev-friendly.Integrated Metis AIPU with 214 TOPS for multi-stream, multi-model AI workloads 16 GB RAM for the CPU + 4 GB for the AIPU, with storage and connectivity for almost any setup Comes with Voyager SDK and BSP for fast prototyping and deploymentThere’s a product brief attached if you want to see a few more details, too.Bonus: pre-orders get 15% off. Shipping is slated to begin in June 2025, and you get 15% off for pre-ordering.Check it out: