Axelera AI

Congratulations to Hewlett Packard Enterprise and the entire HammerHAI consortium on this milestone. EuroHPC Joint Undertaking (EuroHPC JU) has signed a contract to deploy HammerHAI, an AI-optimized supercomputer at the High-Performance Computing Center Stuttgart, as part of the EU's AI Factories initiative. Delivering more than 15 exaflops of peak AI inference performance, it will give European startups, SMEs, and researchers access to world-class AI compute, free of charge. We are proud that Axelera AI's inference hardware is part of this system, and thrilled to see this kind of collaboration driving Europe's sovereign AI infrastructure forward. eu1.hubs.ly/H0sPY4h0 #AxeleraAI #HammerHAI #EuroHPC #AIFactories #EdgeAI #EuropeanAI #Semiconductors

We asked the Axelera AI community to embed intelligence into the places they live, work, and play. They came back with gesture-controlled smart homes that feel like something out of Iron Man. Privacy-first activity sensors running 24/7 with zero video leaving the device. Security systems that catch intruders crawling under blankets. On-device physiotherapy assistants. AI-powered book cataloguers for libraries. Healthcare robots with clinical partners already lined up. Amazing AI applications, each offering different takes on what "smarter spaces" means. All running on Metis hardware with the Voyager SDK, all offline-first, and all built and documented openly by our awesome community members. We've picked our winners. Go see who made the podium and check out what every team built, and join us in congratulating everyone who entered: eu1.hubs.ly/H0sPFPZ0 And if this has you thinking about what you'd build with Metis, our Demo Jam is live right now. Share something cool you've made, and you could win a 4 Quad-Core Metis PCIe Card! Details on the community.

Scaling AI at the Edge: Insights from MWC Barcelona Most AI today is still tethered to the cloud. Why? Because the industry has lacked a solution that combines high performance with the price efficiency needed for true edge deployment. At MWC Barcelona, our CEO and Co-Founder, Fabrizio Del Maffeo, shared how Axelera AI is changing this narrative. By building a hardware architecture from the neural network up, we are enabling enterprises to run powerful AI efficiently right where the data is created. Key Takeaways: Digital In-Memory Computing: Our unique architecture merges memory and computing on a single chip to deliver high throughput and low cost. The Power of Ecosystems: Real-world AI success isn't just about the chip. It requires a synergy of hardware, software, and strong partnerships with industry leaders like Dell Technologies, HP, and Lenovo. What’s Next: We are preparing for a future where world models and advanced sensing will redefine how devices interact with the world. Watch the highlights below to see how we're bringing the future of computer vision and edge inference to life. #EdgeAI #AIInference #ComputerVision #MWC26 #AxeleraAI #Innovation

We're excited to announce our partnership with DeGirum, bringing their PySDK and face recognition platform to Axelera AI's Metis® edge AI accelerators for a powerful, production-ready edge AI solution. What our customers get with DeGirum: * Industry-leading inference performance on Metis hardware * An easy-to-use platform for building and deploying AI solutions * An accessible platform that removes barriers to edge AI deployment * Axelera customers receive one year of premium technical support from DeGirum at no cost The best edge AI outcomes come from pairing the right software with the right hardware. That's exactly what this partnership delivers. Read the full announcement: eu1.hubs.ly/H0sKxpT0 #EdgeAI #ComputerVision #AIAcceleration

AI-driven video analytics will be the biggest topic at ISC West next week. The Metis AIPU is powerful enough for your toughest challenges when applying AI to security. We would love to show you how. You'll be able to see six live demos that show what edge AI looks like when it actually works in the field. No cloud dependency. No latency tradeoff. No compromises on privacy. A few highlights: * A robot dog that identifies threats and recognizes personnel entirely onboard * 8K video processing at over 600 frames per second across 16 streams * Four independent AI pipelines running simultaneously on a single chip * Real-time face detection and crowd monitoring in 8K resolution If you have a specific project in mind, book a 1:1 with our team and we will make sure the conversation is worth your while. Booth 31087, The Venetian Expo Wednesday to Friday, March 25 to 27, Las Vegas Read more and book a meeting: eu1.hubs.ly/H0sHJlp0 #AxeleraAI #ISCWest #ISCWest2026 #EdgeAI #PhysicalSecurity #VideoAnalytics #ComputerVision

At this week’s NVIDIA GTC, much of the conversation will focus on the infrastructure powering the next wave of AI. One concept gaining traction is the idea of “AI factories.” Data centers designed to convert energy and data into intelligence at scale. Ahead of GTC, Alexis sat down with theCUBE Research for a panel to explore that idea and what it means for the future of AI infrastructure. Training builds the models. Inference delivers the value. Every recommendation, vision system, assistant, or autonomous decision happens at inference time. Which means the future of AI infrastructure will not just be about bigger training clusters. It will be about running inference efficiently, everywhere. Watch the conversation: eu1.hubs.ly/H0sHJZQ0 #AIInfrastructure #AIInference #EdgeAI #GTC

Axelera AI has been named one of Europe's Top 100 Rising Startups by VivaTech a list curated in partnership with Accel, Eurazeo, HV Capital, Northzone and Partech. The criteria matter here. This list recognizes companies with a minimum of 40% annual growth over three years and proven recurring revenue. It is a recognition of momentum. For us, that momentum is built on a clear conviction: advanced AI processing should be accessible to any innovator building at the edge, not just the best-funded projects. The traction we are seeing tells us that conviction is resonating. Proud to be recognized among Europe's most promising technology companies, and excited for what comes next. Explore the full list: eu1.hubs.ly/H0sCmmY0 #AxeleraAI #Top100RisingEuropeanStartups #VivaTech #EdgeAI #EuropeanTech #Semiconductors

Nuremberg, that was a good one! 3 days. 18 live demos. 6+ booths. Countless conversations over coffee (yes, we had a barista). Unsung hero of Embedded World: the person who put 'in-booth barista' on the planning list. Embedded World reminded us why we do this. The edge AI space is moving fast, and the people building in it are hungry for hardware that keeps up. We showed what that looks like in practice: real workloads, real performance, no shortcuts. A huge thank you to the partners who made it possible. WebOccult, Kudelski Labs, SpanIdea Systems, Ultralytics, Prodrive Technologies, Intel, MICROIP, VINTECC, WGTech - Workgroup Technology Partners, Micron Technology, Advantech, Axiomtek, Syslogic_AI, and everyone else who brought their best to Hall 5. And to our team, who pulled it off flawlessly across three packed days. The SDK keeps improving. The partner program keeps growing. And Europa, our next generation AIPU, is on its way. Next stop: ISC Security Events West. See you in Las Vegas! #AxeleraAI #EmbeddedWorld #EmbeddedWorld2026 #EdgeAI #ComputerVision #Europa

Axelera AI x Meridian Data Labs Defense installations. Remote industrial sites. Aircraft and engine MROs. Safety-critical metrology inspections. X-ray baggage inspections. These are environments where AI inference must operate under real-world constraints, not in datacenter conditions. Meridian Data Labs, based in Hyderabad, India and Toronto, Canada, caters to these scenarios with its on-premise platforms: Honeycomb for real-time edge orchestration and DISy for AI-powered digital inspection. Together, we're combining their mission-critical software with our Metis AIPU to enable high-performance inference where it's needed most. Our digital in-memory computing (DIMC) architecture is purpose-built for AI acceleration, delivering strong throughput per watt and per dollar in compact, rugged form factors. That makes it a natural fit for the environments Meridian's customers operate in, from predictive maintenance and perimeter security to drone analytics and aeroengine blade inspection. This is what a good partnership looks like: complementary strengths, shared conviction that edge AI should be accessible and efficient, and real deployments that prove it. #AxeleraAI #MeridianDataLabs #EdgeAI #AIInference #DIMC #DefenseTech #DigitalInspection #ComputerVision

Launching Demo Jam: a new AI demo showcase for the Axelera AI community. 💡If you're working with Metis and Voyager SDK, we want to see what you're building, learning, and figuring out. Record a short demo video, tutorial, post or repo and share it on the community. You you could win a top-of-the-line 4 Quad Core Metis PCIe card worth $1,800. This isn't about perfect, polished projects. We're looking for the real stuff at the edge of AI. Works-in-progress, installation tips, optimization tricks, troubleshooting solutions. If it helps someone learn something, it counts. It could also be a fully operational AI project too, of course! 👉 The doors are open already. Details and how to get involved are right here: eu1.hubs.ly/H0sytM30 See you there! Come and share your Metis moments. #EdgeAI #AIHardware #DeveloperCommunity #Metis #VoyagerSDK

The gap between a camera capturing an event and a system understanding it in real time. That is the problem we solve. If you are headed to ISC West in Las Vegas this month, come see what real-time AI inference looks like when it runs entirely at the edge, no cloud dependency, no latency tradeoff, no compromise on privacy. We'll have live demos running across security, video analytics, and autonomous systems, including: * A robot dog from Kudelski Labs that identifies threats and recognizes personnel entirely onboard * 8K video processing at over 600 frames per second across 16 streams * Four independent AI pipelines running simultaneously on a single chip * Real-time face detection, crowd monitoring, and object segmentation across multiple streams If you are building security products and want to understand what purpose-built edge AI can do for your roadmap, book a 15-minute demo with our team. Booth 31087, The Venetian Expo March 25 to 27, 2026, Las Vegas #AxeleraAI #ISCWest #ISCWest2026 #EdgeAI #PhysicalSecurity #VideoAnalytics #ComputerVision

The AI training era is reaching its limit. While the world is obsessed with $100B "Gigafactories," we’re looking at what happens next. At MWC Barcelona, Axelera AI CEO Fabrizio Del Maffeo sat down with theCUBE to discuss the Inference Era. The architectural reset of the computing world is not a distant goal. The infrastructure to support 20 billion intelligent devices is being designed and deployed today. The shift is here: 🔹 From Training to Inference: 80% of the AI chip market is moving to the edge. 🔹 From Centralized to Distributed: Turning base stations and vehicles into mini AI factories. 🔹 From Power-Hungry to Efficient: 214 TOPS at just 10 watts. Watch the full interview with John Furrier and Dave Vellante below. #EdgeAI #Inference #AxeleraAI #MWC26 #Semiconductors eu1.hubs.ly/H0ssZ0b0

"The demos are running, the conversations are flowing, and this evening we are adding drinks to the mix. Join us and our friends at Kudelski Labs for a happy hour at Booth 5-237 today from 4 to 6 PM. If you have been on your feet all day navigating Hall 5, come take a break with the people building the future of edge AI. No agenda. Just good company, cold drinks, and the kind of conversations that do not happen in scheduled meetings. We will be back tomorrow from 4 to 6 PM as well if Tuesday does not work for you. See you there. Booth 5-237, Hall 5 Today 4 to 6 PM, co-hosted with Kudelski Labs Wednesday 4 to 6 PM #EmbeddedWorld #EdgeAI #AxeleraAI #EmbeddedWorld2026"

In space, there is no patch Tuesday. No maintenance windows. No replacements. No second chances if hardware fails mid-mission. The algorithms are only part of the equation. The real challenge is building silicon that survives radiation, temperature extremes, and years of autonomous operation, while still delivering the compute throughput that demanding applications like real-time image processing and autonomous navigation actually require. This article in SpaceNews breaks down exactly what it takes, from radiation hardening and fault tolerance to supply chain longevity and software support over mission lifecycles that span decades. It also makes the case for why the path forward requires space agencies and AI hardware developers to work together, not in parallel. Worth a read if you are working on the hardware or systems side of space AI. eu1.hubs.ly/H0sn3TQ0 Written by Laurent Hill, Gianluca Furano, and Livia Manovi from the European Space Agency, and our own Jean Vieville, Director of Channel and OEM Sales EMEA at Axelera AI. #AxeleraAI #SpaceAI #EdgeAI #EarthObservation #Semiconductors #SpaceTech #ESA

Everyone's talking about the $250M. The part worth thinking about: @BlackRock is in the round. BlackRock manages infrastructure assets, not startup bets. Their participation signals that edge AI compute is starting to look less like a tech venture and more like critical infrastructure. Data centers are hitting hard limits on power and cooling. That problem doesn't get solved by building more data centers. ⚡ Great piece here by @startuprise_eu that brings this to the surface: eu1.hubs.ly/H0smM0S0 #EdgeAI #AIInfrastructure

.@AxeleraAI raised $250M to double down on their more energy - and cost-efficient chips. Louis Mather VP Strategy explains how you structure a $1/4 Billion fundraise: "The further into fundraising you get, the more time it takes to set up the process, to get the right investors involved." "We were very lucky in the sense that we found a great group of supporters in Europe who wanted to back a European company — a European company that operates globally with customers globally, but ultimately a European headquartered company." "We assembled the round from a few different sources. We had a classic VC lead, Innovation Industries, a Dutch deep tech firm. They're the ones that dug most into the due diligence and set the terms." "Then strong support from strategic Samsung Catalyst Fund invested and sovereign funds as well." "I think it's one of the advantages we have in Europe — we have quite a decentralised pool of sovereign funds. Each of the nations in Europe will have a sovereign fund. We had great support from the Belgian, the Italian, and the Dutch sovereign fund." "On top of that, we convinced some fantastic new investors — SoftBank Capital, BlackRock as well" The new round makes it one of Europe's best-funded chip startups and the largest we've ever had on the show.

We were thrilled to have our CMO and President of Americas, Alexis Crowell, join John Furrier on Siliconangle theCUBE at the NYSE to discuss the future of AI Factories and the Intelligent Edge. As AI shifts from training to massive scale deployment, the bottleneck is not just performance; it is power and proximity. At Axelera AI, we are redefining the infrastructure for Physical AI through our Digital In-Memory Computing, bringing high-performance inference to a 4-8W power envelope. As Alexis shared during the interview: "There has not really been a good success story of someone starting in a data center and being able to scale that infrastructure into an edge environment. We think we have got the starting point right because now we have performance and power efficiency that can scale into server solutions." Watch the full interview to hear more about our upcoming Europa line and how we are scaling from the edge to the data center. Full video (14:28): eu1.hubs.ly/H0sgVz70 #NYSEWired #edgeai #aiinference #aiaccelerators #aihardware #aimarket

Barcelona is ready for the IQ Era. Axelera AI is providing the power. MWC 2026 kicks off, we are at the Fira Gran Via to show how the Metis and Europa AIPUs enable high performance AI at the edge without the energy constraints of traditional GPUs. Visit us at the Netherlands Pavilion to see real time computer vision and generative AI hardware in action. Move your intelligence out of the cloud and into the real world. Booth: CS54, Congress Square (4YFN Area) Dates: March 2 to March 5 Book a meeting: eu1.hubs.ly/H0s8xbF0 #AxeleraAI #MWC26 #EdgeAI #Barcelona #ComputerVision

The Axelera AI logo across the NYSE trading floor. A better visualization of where things stand does not exist! But there's more in this week's announcement than the epic $250 million in funding. Over the life of a model, inference costs 15x more than training, and inference utilization is growing at 31x per year. Those are the maths that explain why AI infrastructure investment is shifting. Training gets the headlines. But inference is where the real economics play out, at scale, in production, day after day. The question of where that inference runs, how much power it draws, whether it keeps data local or ships it to a data center, those are the decisions that will define which AI deployments actually make it out of pilot and into the real world. Worth thinking about, just as much as epic funding rounds! Take a closer look: eu1.hubs.ly/H0s766l0 #EdgeAI #AIInference 🏛️

Today, we announced more than $250 million in new funding, led by Innovation Industries with BlackRock and SiteGround Capital joining as new investors alongside many of our original backers doubling down. Total capital raised now exceeds $450 million, making this the largest investment ever in an EU AI semiconductor company. This funding isn't the story. It's a signal that the problem we set out to solve is real, urgent, and large. Most edge AI deployments today are still being built with hardware that wasn't designed for the job. Adapted datacenter chips, power budgets that don't survive procurement, thermal constraints that kill reliability in the field. The gap between what AI can do and what actually works in production is still enormous. That's the problem we set out to solve. Shipping to our 500th customer across manufacturing, retail, defense, robotics, and agritech tells us we're on the right track. And we're just getting started. Here's what comes next: Metis continues to scale globally, giving customers the performance they need within the power and thermal budgets of physical AI. Europa, our next-generation AIPU at 629 TOPS of INT8 performance, begins PCIe accelerator shipments in the first half of 2026. Workloads that were cloud-only are about to run at the edge. Then, Titania, backed by the €61.6M EuroHPC DARE grant, will extend our architecture into HPC and data center environments. And our Partner Accelerator Network keeps growing, because hardware alone doesn't win. The ecosystem around it does. None of this happens without the partners, customers, investors, and employees who believed in what we were building before it was obvious. Thank you. It's still day one, and we're just getting started. #AxeleraAI #EdgeAI #AIInference #AIHardware #Semiconductors #EuropeanTech eu1.hubs.ly/H0s1HSR0