Why Ultralytics YOLO26 matters for your projects:

The architecture is designed end-to-end, which means no more NMS (non-maximum suppression) post-processing. That translates to simpler deployment and genuinely faster inference. It talks about up to 43% speed improvements on CPUs compared to previous versions. For anyone running projects on Orange Pi, Raspberry Pi, or similar setups, that’s a nice boost.

Small object detection also gets a nice bump thanks to ProgLoss and STAL improvements. If you’re working on anything that needs to catch smaller details (maybe retail analytics, inspection systems, drone footage analysis), this should be super interesting.

Ultralytics YOLO26 comes in n/s/m/l flavours across all the usual tasks: detection, segmentation, pose estimation, oriented bounding boxes, and classification. Good options for the speed vs. accuracy tradeoff based on your hardware and use case.

Bug fixes and stability improvements:

Beyond Ultralytics YOLO26, this release cleans up several issues from v1.5.2. Resource leaks in GStreamer and AxInferenceNet pipelines are fixed, segmentation faults when recreating pipelines with trackers are sorted, and there’s better performance for cascaded pipelines with secondary models.

If you’ve got systems with multiple Metis devices, there’s also a deadlock fix for setups with more than eight of them.

Get it now:

Head over to the usual spots to grab v1.5.3. If you’re already running projects on earlier versions, the stability fixes alone make this a welcome update.

The post Voyager SDK v1.5.3 is Live, and That Means Ultralytics YOLO26 Support appeared first on Edge AI and Vision Alliance.

Huge performance shift that opens up seriously scalable edge AI.

Key specs:

• 856 TOPS (INT8)
• Choice of 16GB and 64GB DRAM
• ~12,800 FPS on ResNet-50
• Runs dozens of streams or parallel models per board
• 30–58W typical power draw

It’s not just the raw speed, it’s the ability to compress multi-camera inference, object detection, tracking, segmentation, and more into a single card that I find especially exciting. You can prototype in days, using the Voyager SDK’s YAML-based pipeline builder and model zoo (everything from YOLOv5 to small LLMs).

The benchmarks are where it gets interesting. YOLOv5m hits 1539 FPS at 640×640! YOLOv7 manages 859 FPS, YOLOv8l gets 720 FPS. For context, that’s enough to process dozens of camera streams simultaneously without breaking a sweat.

If you’re testing edge-heavy ideas (multi-stream CV, robotics, smart cities), this is one to keep on your radar. Any thoughts on what you might build with a beast like this?

https://store.axelera.ai/products/pcie-ai-accelerator-card-powered-by-4-metis-aipu

The post The New Metis PCIe with 4 Quad-Core AIPUs is Here appeared first on Edge AI and Vision Alliance.

Eindhoven, NL – October 21, 2025 – Axelera AI, the leading provider of purpose-built AI hardware acceleration technology, today announced Europa, an AI processor unit (AIPU) that sets a new performance/price standard for multi-user generative AI and computer vision applications. Europa’s combination of processing power, energy and thermal efficiency, compact packaging, and multiple form factor options make it ideal for compute-intensive, multi-modal AI inference applications from the edge to enterprise servers. Designed to be cost effective and accessible, Europa enables any organization to unlock the power of cutting-edge AI applications.

Next Gen Architecture For Real World AI Processing Power

The Europa AIPU features eight second-generation AI cores, each incorporating Axelera’s advanced Digital In-Memory Compute (D‑IMC) technology and large vector engines, delivering up to 629 TOPS at INT8 precision. Complementing the AI cores are two clusters of eight dedicated RISC‑V vector processing cores for non-AI pre- and post-processing, achieving a peak performance of 4915 GOPS. An integrated H.264/H.265 decoder further offloads media tasks, enabling customers to reserve the host CPU entirely for business logic and application-level workloads. These cores, programmable through the Voyager SDK, will provide better total cost of ownership than having to offload to other hardware.

Europa’s purpose-built architecture eliminates memory bottlenecks by integrating 128MB of on-chip L2 SRAM and 256-bit LPDDR5 interface to provide 200GB/s bandwidth. This high throughput design delivers 3 to 5 times performance efficiency (performance per watt and performance per dollar) over the leading industry solutions in the same product category, as well as delivering best-in-class performance for generative AI solutions.

“Organizations shouldn’t have to choose between the raw compute power they want and the real-world usability they need,” said Fabrizio del Maffeo, CEO of Axelera. “Europa makes enterprise class AI processing power available to nearly anyone. From manufacturing automation to intelligent surveillance to autonomous systems, Europa enables the next generation of breakthrough AI applications without compromise, complexity or massive budgets. We’re changing the equation of what’s possible with AI at scale.”

With its Europa and Metis AIPU platforms, Axelera offers a full range of accessible AI accelerator solutions for everything from very low-power, size constrained edge device applications to more demanding and performance intensive use cases including humanoid robotics and enterprise server solutions. Across its product lines, Axelera’s emphasis on optimizing processing power and energy efficiency delivers maximum TOPs for any use case. 

Built for Ease of Integration and Deployment

Axelera optimized Europa to simplify design integration and support deployment flexibility. Specifically:

• Europa’s unified architecture simplifies board design by combining specialized AI cores with 16 RISC-V vector processors and a hardware-accelerated HEVC265 decoder to reduce CPU overhead and enable simultaneous real-time processing of visual, language, sensor, and speech workloads with no external requirements.
• With multiple form factors and PCIe 4x Gen4 connectivity, Europa seamlessly integrates with a wide variety of hosts making it easy to upgrade existing edge machines and servers with groundbreaking AI capabilities.
• Europa’s built-in secure enclave technology provides enterprise-grade protection for sensitive workloads.
• Programmable with the same user-friendly Voyager SDK as Metis, developers can easily leverage the same tool to deliver their inference solutions across a wide range of devices and use cases.
• Its compact 35x35mm package maximizes performance density, making it ideal for edge deployments while delivering the processing power to meet server and data center needs.

Powerful Local Processing with Europa PCIe

Axelera will also offer the Europa AIPU integrated in a PCIe card form factor. Europa PCIe cards support scalable configurations –from single-chip 16GB to four-chip 256GB solutions– to meet a wide variety of workload requirements. Leveraging the power of Europa, the cards can process complex workloads locally, and preprocess and decode multiple 4K HEVC265 video streams simultaneously, all with minimal latency and economical power consumption.

Shipments for the Europa AIPU and PCIe card will begin in first half 2026.

Ecosystem Support for Europa

• “IT4LIA’s AI Factory initiative is a strategic cornerstone in building a sovereign European infrastructure for artificial intelligence,” said Daniele Cesarini, Head of AI/HPC Architecture at Cineca. “Our collaboration with Axelera AI within the DARE project reflects our commitment to integrating advanced European technologies into national HPC environments. We are ready to host and validate Axelera’s Europa accelerators within our infrastructure, supporting their deployment in real-world, high-performance AI workloads. This partnership is a concrete step toward a scalable, energy-efficient AI ecosystem, and demonstrates how European innovation in semiconductor design can be effectively translated into operational excellence. By working together, we aim to accelerate the adoption of sovereign AI technologies and reinforce Europe’s leadership in sustainable, high-performance computing.”
• “At SURF, we empower researchers with world-class digital services and drive innovation through collaboration,” said Valeriu Codreanu, Head of High-Performance Computing and Visualization at SURF. “Our partnership with Axelera AI, using Metis in SURF’s Experimental Technologies Platform and exploring Europa, reflects our excitement for emerging AI technologies that have the potential to transform research.”
• “The Ultralytics YOLO family of models has set the industry standard for computer vision globally,” said Glenn Jocher, CEO of Ultralytics. “The performance we’ve achieved running YOLO models on Axelera AI’s Metis platform has been remarkable, delivering the speed and efficiency our users demand for real-world computer vision applications. Our collaboration has proven that advanced AI inference can be both powerful and accessible. With Europa’s expanded capabilities coming next year, we’re excited to broaden YOLO’s deployment across entirely new use cases.”
• “As a company at the forefront of AI innovation, Almawave is excited to collaborate with Axelera AI on the launch of Europa,’’  said Valeria Sandei – CEO Almawave Spa.  ‘’ By combining Axelera’s next-generation inference platform with our expertise in developing cutting-edge AI applications and our proprietary language model Velvet, we can deliver powerful, accessible, and energy-efficient solutions to our customers. This partnership reinforces our shared commitment to bringing advanced AI to the Edge, with real impact across industries.’
• “Advantech has successfully integrated Axelera AI’s Metis AIPU into our products, bringing efficient AI processing to customers worldwide. The real-world performance and reliability have exceeded expectations, enabling breakthrough applications in manufacturing automation and intelligent infrastructure. We’re thrilled to support the Europa launch and look forward to incorporating its 629 TOPS of processing power into our enterprise and industrial server solutions. This continued partnership ensures our customers have access to purpose-built AI technology that delivers exceptional performance per watt and per dollar, making advanced AI inference accessible for the most demanding industrial applications,” said Joey Hsu, Embedded_ECG Director at Advantech.
• “SECO is a leading provider of Edge AI solutions, empowering customers to bring intelligence and efficiency directly to their devices,” said Maurizio Caporali, Chief Product Officer at SECO. “We integrated Metis into our Edge AI product line earlier this year and have been impressed by the significant boost in performance and scalability it delivers. We are excited to partner with Axelera as they continue to expand their world-class inference portfolio and enable even broader adoption of AI at the edge across industries.”
• “As the leading provider of AI-software, Multiverse prides itself on partnering with the very best technology companies to enable our solutions,” said Rodrigo Hernandez, Global Director of Gen AI at Multiverse Computing. “Axelera AI is building world-class hardware that powers the most performant and energy efficient AI inference solutions around the globe. Their next generation of hardware, Europa, will be a welcome addition to our infrastructure as we pursue our mission to make AI faster, cheaper and more energy efficient.”
• “E4 Computer Engineering is widely renown as being leader on integrating the latest technology solutions,” said Cosimo D. Gianfreda, CEO and Co-Founder at E4. “We are testing Metis from Axelera AI and are very impressed with its capabilities as well as of the support provided by the Voyager SDK. We firmly believe that the next solution, Europa, offers a leap in performance such that data centers will more efficiently support the needs of their customers and we are prepared to integrate this new solution into our ecosystem!”
• “This production exemplifies Samsung’s commitment to empowering AI innovation across the globe,” said Taejoong Song, vice president of Foundry Technology Planning Team at Samsung Electronics.  “By manufacturing Axelera AI’s breakthrough architecture with our competitive 5nm process technology, we’re enabling the next generation of edge AI applications that will transform industries from manufacturing to healthcare. This engagement demonstrates how Korean semiconductor excellence can support European AI innovation.”

About Axelera AI

Axelera AI is the leading provider of purpose-built AI hardware acceleration technology for AI inference, including computer vision and generative AI applications. Its first-generation product is the game-changing Metis AI platform – a holistic hardware and software solution for Edge AI inference which delivers the world’s highest performance and power-efficiency at a fraction of the cost of alternative solutions. Headquartered in the AI Innovation Center of the High Tech Campus in Eindhoven, The Netherlands, Axelera AI has R&D offices in Belgium, Switzerland, Italy and the UK, with more than 200 employees in 18 countries. Its team of experts in AI software and hardware hail from top AI firms and Fortune 500 companies.

The post Axelera Announces Europa AIPU, Setting New Industry Benchmark for AI Accelerator Performance, Power Efficiency and Affordability appeared first on Edge AI and Vision Alliance.

EINDHOVEN, NL – September 8, 2025 – Axelera AI, the leading provider of purpose-built AI hardware acceleration technology, today announced Metis® M.2 Max, a new addition to the company’s class-leading Metis AI processor unit (AIPU) family. Delivering the performance of a PCIe card in the M.2 form factor, Metis M.2 Max is designed for the most compute-intensive AI inference applications at the edge, including better performance for large language models (LLMs) and vision transformer networks.

Metis M.2 Max enhances the current Metis M.2 with double the memory bandwidth, a slimmer profile, advanced thermal management features and additional security capabilities. Metis M.2 Max will have up to 16 GB of memory. In addition, Axelera will offer versions of Metis M.2 Max for both standard operating temperature range (-20°C to +70°C) and extended operating temperature range (-40°C to +85°C) for harsh environments. These enhancements make Metis M.2 Max ideal for applications in industrial manufacturing, retail, security, healthcare and public safety.

“We continue to set the price-performance ratio benchmark for the AI accelerator market,” said Fabrizio del Maffeo, CEO of Axelera AI. “Our goal is to make it possible for our customers to deploy transformative edge AI applications at scale. Metis M.2 Max and our original Metis M.2 card enable customers to choose the solution that best fits their requirements – from computer vision to large language models to the latest of transformer models. We are also adding enhanced security to better address the growing threat landscape at the edge.”

Metis M.2 Max builds on Axelera AI’s proven Metis AIPU and offers high performance and efficiency for large, demanding models such as vision and GenAI, inclusive of LLMs and vision-language models (VLMs). M.2 Max delivers a 33% performance uplift in convolutional neural networks (CNNs) and double the token/second for LLMs and VLMs, all while staying within a typical average power range of 6.5W

With security being paramount at the edge, the Metis M.2 Max incorporates enhanced security features including firmware integrity protection through a securely provisioned Root of Trust, enabling secure boot and secure upgrade capabilities. These security measures operate transparently, requiring no user intervention while helping ensure only authenticated Axelera AI-issued firmware runs on customer systems.

Metis M.2 Max, a 2280 M.2 M-key module, will be available as a standalone board or with an optional low profile heatsink. This design reduces the height of the card by 27% over the current M.2 card, allowing a wider range of configurations. Also, for users that require AI capabilities in power- or thermal-constrained deployments, an onboard power probe can be used to automatically adjust performance to specific settings.

Axelera AI makes it easy for developers to incorporate Metis M.2 Max into their AI projects with the Voyager SDK. Voyager unlocks the full potential of Metis AIPUs and simplifies deployment of proprietary and industry standard models.

Metis M.2 Max starts shipping in Q4 2025 from the Axelera AI Webstore or via Axelera AI Channel Partners.

About Axelera AI

Axelera AI is the leading provider of purpose-built AI hardware acceleration technology for AI inference, including computer vision and generative AI applications. Its first-generation product is the game-changing Metis AI platform – a holistic hardware and software solution for Edge AI inference which delivers world’s highest performance and power-efficiency at a fraction of the cost of alternative solutions. Headquartered in the AI Innovation Center of the High Tech Campus in Eindhoven, The Netherlands, Axelera AI has R&D offices in Belgium, Switzerland, Italy and the UK, with more than 180 employees in 18 countries. Its team of experts in AI software and hardware hail from top AI firms and Fortune 500 companies.

The post Axelera AI Boosts LLMs at the Edge by 2x with Metis M.2 Max Introduction appeared first on Edge AI and Vision Alliance.

Florentino showcases two specific demos with different use cases. The first is a DEEPX accelerator with Micron LPDDR5X connected to a Raspberry Pi module, also with Micron memory onboard. The second is with Axelera and their Metis AI platform, full of Micron’s LPDDR4 running four simultaneous video language models (VLMs).

The post Micron Demonstration of Its Key Partner Enablement, Driving Solutions for AI and VLMs at the Edge appeared first on Edge AI and Vision Alliance.

As part of the DARE consortium, Axelera AI will support the EuroHPC JU and its effort to develop a World Class Supercomputing Ecosystem in Europe. DARE aims to foster the design and development of European processors, accelerators, and related technologies for extreme-scale, high-performance, and emerging applications.

“Our D-IMC technology leverages a future-proof, scalable multi-AI-core architecture, ensuring unparalleled adaptability and efficiency. Enhanced with proprietary RISC-V vector extensions, this versatile mixed-precision platform is engineered to excel across diverse AI workloads,” explained Evangelos Eleftheriou, CTO and co-founder of Axelera AI. “Uniquely, our architecture facilitates scaling from the edge to the cloud, streamlining expansion and optimizing performance in ways that traditional cloud-to-edge approaches cannot. We are setting a new standard for AI infrastructure, making true scalability a tangible reality.

Why it matters:

The AI market is growing at 28%+ CAGR with the vast majority of that expansion driven by inference. However, existing concerns around performance, cost, efficiency and sustainability of cloud-based solutions are intensifying due to industry advancements. Innovations such as reasoning models (i.e. OpenAI-o1 and DeepSeek R1) require significantly more inference computing than earlier transformer models. Targeting a deployment date of 2028, Axelera AI’s Titania is engineered to address these challenges by delivering superior throughput and efficiency for data-intensive AI applications and future zetta-scale HPC centers at a competitive price.

To support this development effort, Axelera will grow its research and development teams in the Netherlands, Italy and Belgium.

How it works:

The Titania chiplet-based architecture will leverage the company’s unique D-IMC technology along with RISC-V capabilities, to meet the increasing AI demands across various market sectors, including HPC, enterprise data centers, robotics, automotive, and others, while maintaining the efficiency of an edge-oriented architecture. Leveraging D-IMC allows for near-linear scalability in performance without the significant power and cooling overhead typical of other solutions. Integrating RISC-V technology with vector extensions enables Axelera AI to rapidly innovate in response to evolving customer needs. Multiple Titania chiplets will be packaged in a System-in-Package (SiP).

“This is an important milestone and validation of our technology. Since Axelera AI was founded in July 2021, we have continuously delivered technologies to help customers tackle the AI industry’s biggest challenges and efficiently implement AI capabilities into their products,” said Fabrizio Del Maffeo, Co-Founder and CEO at Axelera AI. “Today, we deliver a cutting-edge hardware and software platform for accelerating computer vision on edge devices at a fraction of the cost and energy consumption of current solutions. Titania builds upon this unique product suite. We’re grateful to the EuroHPC DARE Project and the countries involved for helping accelerate the development of this groundbreaking AI inference technology for HPC data centers.”

The EuroHPC JU was established to develop, deploy, extend and maintain an integrated world-class supercomputing and quantum computing infrastructure to foster and support a highly competitive and innovative HPC ecosystem. Axelera AI’s Titania technology is ideal for building extremely scalable, energy-efficient and highly resilient HPC and data center technologies.

“I am proud to announce the launch of the DARE project which marks a significant milestone for European digital sovereignty,” said Anders Jensen EuroHPC JU Executive Director, “This ambitious initiative will drive innovation in both hardware and software technologies and leverage the full power of HPC and AI to develop secure, efficient and European-led solutions for the future.”

The development of Titania seamlessly aligns with Axelera AI’s mission to democratize AI and complements the company’s current product offerings. This includes the Metis AI Platform that simplifies the development, integration and deployment of AI inference acceleration and achieves a 3-5x increase in efficiency and performance. To learn more about current and future product offerings from the edge to the data center to address the growing computing needs for generative AI, large language models and large multi-modal models, visit us at Axelera.ai

Accelerate your innovation now with the Metis AI, available for ordering.

About Axelera AI

Axelera AI is the leading provider of purpose-built AI hardware acceleration technology for AI inference, including computer vision and generative AI applications. Its first-generation product is the game-changing Metis AI platform – a holistic hardware and software solution for Edge AI inference which delivers the world’s highest performance and energy-efficiency at a fraction of the cost of alternative solutions. Headquartered in the AI Innovation Center of the High Tech Campus in Eindhoven, The Netherlands, Axelera AI has R&D offices in Belgium, Switzerland, Italy and the UK, with more than 200 employees across three continents. Its team of experts in AI software and hardware hail from top AI firms and Fortune 500 companies.

The post Axelera AI Secures Up to €61.6 Million Grant to Develop Scalable AI Chiplet for High-performance Computing appeared first on Edge AI and Vision Alliance.

Adding to the excitement, Axelera AI has been named a CES Honoree for our Metis Compute Board, a recognition that highlights our dedication to pushing the boundaries of AI technology. The Metis Compute Board is a full, single-board computer that will be available for sale shortly. This board is a fully integrated product requiring almost zero development, which allows developers to innovate rapidly and deliver their own solutions quickly.

Here’s a preview of the innovative demos we’ll be showcasing at our suite:

1. Edge Chatbot in partnership with Arduino
   Dive into a demonstration of a powerful 3.8-billion-parameter language model (Phi3-mini) chatbot running on an Arduino board powered by the Metis AIPU and a Portenta X8. We showcase how industrial applications can use locally run language models to provide private and secure conversational interfaces to operators or to run autonomous agents. By combining Portenta’s sensing solution with the Metis LLM inferencing capabilities, the Arduino community will have outstanding potential to solve real-world problems. This demo also highlights our commitment to making high-performance AI accessible, compact, and efficient, even for resource-constrained environments.
2. Real-Time Monitoring for Personal Protective Equipment
   Witness our AI-powered monitoring system for personal protective equipment (PPE). This real-time solution exemplifies how the Metis product line ensures safety and compliance in industrial settings, demonstrating the power of inference at the edge to drive actionable insights in critical environments. . More importantly, this solution was developed with one of the Axelera AI customers, highlighting the ease of use of the Voyager SDK. This same technology can be leveraged in Retail environments, the food and beverage industry, or even medical environments.
3. 24 Live Camera Streams with Automated Object Detection
   Explore the capabilities of the Metis architecture in processing 24 simultaneous live camera streams (on a single Metis AIPU and a standard, off the shelf, desktop computer) with integrated object detection identifying over 60-classes of objects at 800FPS on the Metis AIPU. While this demo is running yolov5n, the Metis-class of systems is capable of supporting multiple models and increased complexity. Object detection is foundational in use cases supporting smart cities, security & surveillance, and industrial automation, just to name a few!
4. Medical Segmentation for Faster Disease Detection
   Our medical segmentation demo offers a glimpse into the future of healthcare. This demo showcases supporting radiologists and oncologists to detect and outline tumors and in defining if a tumor is benign or malignant. By pinpointing areas of concern within the human body, the Metis AIPU empowers medical practitioners to identify potential diseases more quickly and accurately, bringing AI’s transformative potential to life-saving scenarios.

Why Visit Axelera AI at CES?

Our mission is to bridge the gap between cutting-edge AI and practical, real-world applications. At CES, we are inviting you to see how our Metis product line delivers:

• Unmatched Performance at the Edge: High throughput and low latency designed for the most demanding AI workloads.
• Energy Efficiency: Optimal power usage without compromising on performance.
• Seamless Integration: A unified hardware and software solution tailored to your AI needs.

CES attendees will get a firsthand look at how Axelera AI empowers industries ranging from healthcare to smart infrastructure but will also have the opportunity to engage with our team of experts.

Visit us in Eureka Park at the Venetian Expo and experience the future of AI at the edge!

Let’s create a smarter, more efficient world together. See you at CES 2025!

And to stay up to date on the latest from Axelera AI, please contact us here.

The post Axelera AI at CES: Honored to Showcase Innovation at the Edge appeared first on Edge AI and Vision Alliance.

The collaboration will combine the strengths of Axelera AI’s Metis AI Platform with the powerful SOMs from the Arduino Pro range to provide customers with easy-to-use hardware and software to innovate around AI. Users will enjoy the freedom to dictate their own AI journey, thanks to tools that provide unique digital in-memory computing and RISC-V controlled dataflow technology, delivering high performance and usability at a fraction of the cost and power of other solutions available today.

Showcasing AI-Powered Industrial Monitoring at CES 2025

The first outcome of this partnership will be an innovative solution that will integrate AI technology and the Portenta X8, running an offline pre-trained LLM (Phi-3) to power an AI-driven industrial monitoring system capable of processing and analyzing sensor data (temperature, humidity, air quality, CO2, etc.) from different locations and manufacturing machines, to identify trends and potential issues in real time: a demo will be showcased live at CES, January 7-10, 2025 in Las Vegas, NV at the EIC Pavillion (Tech West, Venetian Expo, Level 1, Hall G – Booth #60633 – Eureka Park).

Investing in AI with an Open Approach

As we approach 2025, investments in AI are only expected to increase. IDC recently forecasted that worldwide spending on technology to support AI strategies will reach $337 billion in the upcoming year. The estimate is likely to more than double to $749 billion by 2028 as organizations explore new and innovative use cases such as generative AI and agentic AI – an emerging trend, expected to pick up steam in 2025, that employs autonomous machine “agents” that move beyond query-and-response generative chatbots to accomplish enterprise-level tasks without human guidance. The open approach that Axelera AI and Arduino are taking to bring high-performance inference solutions to the edge will enable these and many other use cases globally.

Extending the Opportunities for Open-Source Innovation

Arduino’s open-source solutions are trusted by many Fortune 500 companies and extensively used by makers, educators, and engineers all over the world, aiming to discover what comes next in their fields of interest. This partnership allows a 33-million-strong community of creative thinkers already working with Arduino to have access to Axelera AI’s innovative AI acceleration platform, to transform AI technologies and unlock new possibilities for AI that have yet to be realized.

“Axelera AI was founded with a vision to democratize AI by offering fast, easy-to-access AI technology that minimizes power consumption and cost,” said Fabrizio Del Maffeo, CEO and Co-Founder at Axelera AI. “This is critical for companies to realize true AI innovation. Another important step to democratizing AI is building an ecosystem of collaborators all striving to achieve that same goal. We cannot wait to see what the Arduino community will create through this partnership.”

A New Vision for AI Accessibility, Based on Collaboration

The partnership is an important step toward developing an AI ecosystem of partners all aligned on the vision to reduce barriers around the most advanced and powerful technologies today. To realize this multi-billion-dollar opportunity requires skillsets from a wide range of disciplines, including builders, enablers, co-creators, and developers. This ecosystem is essential to harness the true power of AI, and to enable the AI innovation of tomorrow, unlocking AI imagination across key vertical markets such as automotive, digital healthcare, high performance computing, Industry 4.0, retail, robots & drones, visual security and more.

“This partnership exemplifies Arduino’s mission to enable innovators with powerful, accessible tools that bridge creativity and real-world problem-solving,” said Fabio Violante, CEO at Arduino. “By working with Axelera AI, we’re providing developers and businesses the means to integrate advanced AI capabilities into their projects, opening the door to groundbreaking innovations across industries. It’s exciting to see how this collaboration will empower our community and beyond to turn bold ideas into impactful solutions.”

Discover More!

Will you be at CES 2025? If so, set up a meeting with Axelera AI to see a demo and learn about how this collaboration with Arduino aims to unlock the full power of Edge AI. You can book a meeting here: https://www.axelera.ai/visit-axelera-ai-at-ces-2025.

As the Arduino partnership products become ready, they will join the Axelera AI portfolio available for purchase on the our Webshop: https://store.axelera.ai/

The post Axelera AI Partners with Arduino to Extend the Full Power of AI to the Edge appeared first on Edge AI and Vision Alliance.

AiM Future

Booth #9273

AiM Future provides artificial intelligence accelerator IP and software development kits (SDK) to fabless, design house, and FPGA companies in edge computing markets such as IoT, Smart-X, AR/VR, and automotive. Its NeuroMosAIc technology provides scalability, flexibility, configurability and multimodality. For requests to meet at the AiM Future suite, please contact info@aimfuture.ai. 

AIRY3D

Appointment Only

AIRY3D is commercializing the world’s first passive, single-sensor solution for 3D imaging, delivering profound savings in hardware, computation, and power usage. AIRY3D can bring 3D to your existing design in a size that is unmatched by other technologies while maintaining your original 2D image. For requests to meet at the AIRY3D suite, please contact info@airy3d.com.

Au-Zone Technologies Inc.

Appointment Only

Au-Zone Technologies leads in embedded Computer Vision, AI, and Precision technologies, enabling clients to deploy cutting-edge intelligent solutions. With 15+ years of expertise, we partner with OEMs and engineering teams in sectors like Video Telematics, Marine, Space, and Robotics, advancing autonomous machines. For requests to meet at the Au-Zone suite, please visit https://www.edgefirst.ai/. 

Axelera AI

Booth #60633

Axelera AI is delivering the world’s most powerful and advanced solutions for AI at the edge. Its industry-defining Metis- AI platform—a complete hardware and software solution for AI inference at the edge—makes computer vision applications more accessible, powerful and user friendly than ever before. For requests to meet at the Axelera AI suite, please visit https://www.axelera.ai/visit-axelera-ai-at-ces-2025.

BrainChip

Suite 29-312

BrainChip is the global leader in event driven computing, with its Akida platform performing inference at the lowest power on the edge today. Supported by development tools, boards, chips and IP, Akida’s event driven architecture is suitable for a wide range of use cases in speech, audio, video and other sensor data. For requests to meet at the BrainChip suite, please visit https://calendly.com/brainchip/ces-2025.

Cadence

Venetian, Level 3, Ballroom 3001A

Cadence provides a wide range of IP and Silicon Solutions for automotive, consumer, and data center markets, built on decades of interface and processor IP expertise. Our comprehensive IP portfolio includes protocol controllers, PHYs, configurable processors, low power high-efficiency DSPs, AI accelerators, and memory chiplets. 

Ceva

Bassano 2709

At Ceva, we are passionate about bringing new levels of innovation to the smart edge. Our wireless communications, sensing and edge AI technologies are at the heart of some of today’s most advanced smart edge products. We have the broadest portfolio of IP to connect, sense and infer data more reliably and efficiently. For requests to meet at the Ceva suite, please contact events@ceva-ip.com.

CLIKA

Appointment Only

CLIKA simplifies deploying AI on diverse hardware by offering automated AI model compression and format compilation. Our proprietary compression algorithm automatically downsizes AI models by 75% and accelerates inference speed by up to 40x, for any target hardware. For requests to meet at the CLIKA suite, please contact business@clika.io.

Commonlands

Appointment Only

Commonlands is a US-based optics supplier providing high-performance cost-effective M12 lenses, C-mount lenses, and related accessories. Our products are commonly used across surveillance, warehouse robotics, IoT, smart retail, factory automation, and medical industries. For requests to meet with Commonlands, please contact max.henkart@commonlands.com.

D3 Embedded

North Hall, N116

Texas Instruments will showcase D3 Embedded’s full-form-factor Automotive Front Camera Reference Design. D3 Embedded will also be demonstrating automotive in-cabin applications such as driver monitoring and occupant monitoring with STMicroelectronics and Smart Eye in STMicroelectronics’ demo vehicle. For requests to meet at the D3 suite, please contact sales@d3embedded.com.

DEEPX

Booth #9045

Founded in anticipation of an era when artificial intelligence will be as ubiquitous as electricity and Wi-Fi, DEEPX develops the underlying technology for high-performance AI semiconductors and computing solutions that can make all electronic devices intelligent. For requests to meet at the DEEPX suite, please contact sales@deepx.ai.

Digica

Appointment Only

Digica is an independent AI and data science company. We provide customized solutions by applying the latest AI tools. With 8 years of experience, 295 projects, and 90 experts, we specialize in computer vision, deep learning, synthetic imaging, large language models, and predictive maintenance. For requests to meet with Digica, please contact ben@digica.com.

e-con Systems

Booth #9517

e-con Systems has been a pioneer in the embedded vision space, designing, developing and manufacturing custom and off-the-shelf camera solutions since 2003. With a team of 300+ extremely skilled core engineers, our products are currently embedded in over 350 customer products. For requests to meet at the e-con Systems suite, please contact dharmalingam.k@e-consystems.com.

Embedl

Appointment Only

Embedl develops advanced solutions for efficient AI deployment in embedded systems. With nearly a decade of research, we help AI leaders in automotive, defense, and emerging industries build cutting-edge, resource-efficient AI products. Our technology streamlines development, driving innovation and competitive advantage. For requests to meet at the Embedl suite, please contact ola@embedl.com.

ENERZAi

Booth #61507

ENERZAi is an AI software company with cutting-edge AI optimization technology. We will demonstrate our next-generation AI inference engine, Optimium, which accelerates AI model inference on target hardware while maintaining accuracy and facilitates convenient AI model deployment across various hardware using a single tool. For requests to meet at the ENERZAi suite, please contact hanhim.chang@enerzai.com.

eYs3D

Booth #15741

eYs3D brings computer vision-based image processing capabilities to autonomous or unmanned robots, vehicles, and AIoT devices. With our own edge processor with built-in NPU, we provide a cost-effective AI platform that can be easily integrated into various applications to improve performance and enable smart decisions. 

FotoNation

Appointment Only

FotoNation is an innovator of ultra-low-power embedded hardware-accelerated edge AI solutions to enhance signal quality and enable AI analytics. We enable SoC makers to add high quality neural signal processing and analytics to their chips through IP cores and, in the future, by highly efficient FotoNation chiplets. For requests to meet with FotoNation, please contact info@fotonation.com.

Geisel Software

Booth #9649

Meet Symage by Geisel Software, the synthetic data platform built for real results. Symage generates high-fidelity, perfectly labeled image training datasets customized for your specific model. Ditch data labeling and cut your prep time by up to 90%! Stop by our booth for a demo and enter to win a Quest 3 VR headset! For requests to meet at the Geisel Software suite, please contact jr@geisel.software. 

Gimlet

Appointment Only

Gimlet is a developer tool for building, deploying, and monitoring AI at the edge. With Gimlet, you can deploy and monitor AI applications across your edge fleet in minutes. Gimlet helps build and refine custom models using generative AI and optimizes AI applications for your hardware without any manual configuration. 

Hailo

Venetian Tower, Suite# 29-106 and Booth #61701

Hailo develops top-performing AI processors specifically designed to enable AI tasks on the edge. For requests to meet at the Hailo suite, please contact marketing@hailo.ai. 

Inuitive

Appointment Only

Inuitive’s Vision-on-Chip processors and sensor modules offer an all-in-one solution with integrated capabilities, outstanding performance, optimal size, and cost efficiency. They support simultaneous depth sensing, SLAM, and AI-based object detection and recognition, enhancing robotics, AR/VR, AIoT, and 3D sensing applications. For requests to meet at the Inuitive suite, please contact jimt@inuitive-tech.com.

Lattice Semiconductor

Appointment Only

Lattice Semiconductor is the low power programmable leader. We solve customer problems across the network, from the edge to the cloud, in the growing communications, computing, industrial, automotive, and consumer markets. For requests to meet at the Lattice suite, please contact hussein.osman@latticesemi.com.

Microchip

Booth #3404/3405

Join Microchip at CES for an empowering experience of innovation with hands-on and interactive demos showcasing cutting-edge solutions in AI, automotive, and industrial technologies. Microchip is a leading provider of smart, connected and secure embedded control and processing solutions.

Nextchip

Westgate Hospitality Suites

Nextchip demonstrate a full embedded vision system for ADAS and AD. In addition, we will show conventional color camera and thermal imaging/iToF solutions. With sensing fusion, our ADAS SoC will show its performance with reference applications such as SVM and blind spot information system (BSIS). For requests to meet at the Nextchip suite, please contact kjo@nextchip.com.   

NOTA AI

Appointment Only

NOTA AI is a leading edge AI software startup with 100+ global customers. Specializing in AI model optimization, NOTA enables efficient deployment of AI on edge devices. With $50M raised in Series C funding, the company is focused on growth and innovation in the Edge AI space. 

NXP Semiconductors

Booth #CP-107

NXP (NASDAQ: NXPI) is the trusted partner for solutions in auto, industrial & IoT, mobile and comms infrastructure. Our “Brighter Together” way links leading-edge tech with pioneering people forming system solutions making the world better, safer, & secure. We have operations globally and posted revenue of $13+ billion in 2023.

OpenMV

Appointment Only

OpenMV develops OpenMV Cam, an easy-to-use, low-cost, extensible, Python-powered machine vision module. We aim to make OpenMV Cam the “Arduino of machine vision.” For requests to meet with OpenMV, please contact kwagyeman@openmv.io.

Piera Systems

Appointment Only

Piera Systems is expanding our Canāree line of air quality monitoring products to include models designed for hospitality, education and ProTech markets. We are also seeking to expand our network of distributors and value-added resellers, plus entertain parties interested in investing in Piera Systems. For requests to meet with Piera Systems, please contact howard@pierasystems.com.

Quadric

Appointment Only

Quadric—the leading licensor of general-purpose neural processor IP for SoC design—will have representatives at CES 2025 ready to meet with you to discuss your AI inference requirements for your next SoC design.  For requests to meet with Quadric, please contact info@quadric.io. 

Texas Instruments

Booth #N116

Texas Instruments will have a private meeting room showcasing demos for automotive, consumer and audio applications. Through perception and edge AI technologies, we’re helping you reimagine everything from vehicles to robots to personal electronics. For requests to meet at the Texas Instruments suite, please contact EdgeAI_Vision_Alliance_CES2024@list.ti.com.

VeriSilicon

Bassano Booth #2701 and #2702

At CES 2025, VeriSilicon will showcase live demonstrations of its latest technology developments. Attendees can explore cutting-edge solutions firsthand. Private viewings are available by appointment. For requests to meet with VeriSilicon, please contact yao.lu@verisilicon.com.

videantis

Booth #430

videantis is a leading supplier of processing solutions for AI and other compute-intensive DSP processing for automotive, mobile, consumer, robotics, IoT, drones, industrial and other applications with outstanding efficiency, scalability and proven in > 20 million cars on the streets today. For requests to meet at the videantis suite, please contact tony.picard@videantis.com.

Visionary.ai

Booth #61701

Named a 2023 Top 100 AI Startup, Visionary.ai enables cameras to capture clear video in extreme low light and HDR. Our edge AI software enhances video quality in real-time for medical imaging, robotics, ADAS, cinematic, surveillance, consumer, and industrial IoT applications. For requests to meet at the Visionary.ai suite, please contact david.jarmon@visionary.ai. 

The post Alliance Members at 2025 CES appeared first on Edge AI and Vision Alliance.

A single Metis AIPU runs at over 200 TOPs and can run computer vision inference at multiple streams at high frames per second. This allows for fast and cost-effective computer vision inference.

The post Axelera AI Demonstration of the High Performance Achievable with the Metis AIPU appeared first on Edge AI and Vision Alliance.