Latest news with #SmartEdge
Forbes
23-07-2025
- Business
- Forbes
Small Language Models, Big Possibilities: The Future Of AI At The Edge
Iri Trashanski, Chief Strategy Officer at Ceva, is shaping the future of the Smart Edge with extensive experience across tech sectors. The AI landscape is taking a dramatic turn, as small language and multimodal models are approaching the capabilities of larger, cloud-based systems. This acceleration reflects a broader shift toward on-device intelligence. As the industry races toward AI that is local, fast, secure and power-efficient, the future is increasingly unfolding on the smallest, most resource-constrained devices at the very edge of the network. From wearables and smart speakers to industrial sensors and in-vehicle systems, the demand is growing for language-capable AI that can operate independently of the cloud. As small language models (SLMs) continue to improve, they are poised to play a key role in making language AI more accessible across a wide range of embedded applications. The New Edge Imperative Device makers are pushing to reduce latency, strengthen privacy, lower operational costs and design more sustainable products. All of these point to a shift away from cloud-reliant AI toward local processing. However, delivering meaningful AI performance in devices with tight power and memory budgets isn't easy. Traditional approaches fall short, and hardware like the $95,000 "desktop supercomputer," capable of running full large language models (LLMs) offline, while impressive, is cost- and energy-prohibitive for mass deployment. By contrast, SLMs running on ultra-efficient processors offer a practical and sustainable path forward. Breakthroughs like Microsoft's Phi, Google's Gemini Nano and open models like Mistral and Metalama are closing the performance gap rapidly. Some models—like Google's Gemma 3 and TinyLlama—are achieving remarkable results with only around one billion parameters, enabling summarization, translation and command interpretation directly on-device. Optimizations such as pruning, quantization and distillation further shrink their size and energy draw. These models are already running on consumer-grade chipsets, proving that lean, localized intelligence is ready for prime time. Bridging The Gap In Edge AI Deployment As someone working closely with global chipmakers and system designers, I see this trend as a strategic inflection point. The industry is shifting toward AI that is leaner, faster and embedded where decisions happen—where milliseconds matter, and where compute resources are tightly bound. As I attend events like Embedded World 2025, it has become clear that the appetite for intelligent edge solutions is growing faster than the infrastructure needed to support them. Device manufacturers want to bring AI to the edge—but face a fragmented ecosystem of silicon platforms, development tools and AI frameworks. Recent research shows that edge AI adoption is rapidly growing across industries. The global edge AI in smart devices market is forecast to exceed $385 billion by 2034, according to research. The challenge is how to bridge the gap between today's state-of-the-art models and tomorrow's real-world deployment requirements. This means ensuring models not only fit into the tight power and memory budgets of edge devices—but that they can be deployed easily, updated efficiently and scaled cost-effectively. Many device manufacturers are also struggling to bridge the 'last mile' of inference: ensuring models not only run locally but can be maintained, updated and scaled cost-effectively. Building Blocks For The Smart Edge To solve these challenges, organizations across the tech ecosystem—from global chipmakers and tool vendors to consumer device manufacturers—are coalescing around a shared vision: The smarter future of AI lies at the edge. This shift is fueled by increasing demands for real-time responsiveness, privacy-preserving data handling, lower latency and more sustainable compute alternatives—particularly in scenarios like wearables, automotive systems and industrial IoT. Recent surveys show that a majority of enterprises are either deploying edge AI or planning to do so imminently, reflecting how on-device inference has shifted from experimental to strategic realms. This momentum is supported by advancements across multiple fronts: edge-ready NPUs and accelerators embedded into devices, lightweight model formats like TensorFlow Lite and ONNX Runtime and hybrid cloud—edge architectures that offer flexibility and scale. As AI capabilities become leaner and more optimized, the value of real-time, intelligent inference at the device level is accelerating not just across verticals like automotive, consumer electronics and industrial systems, but as a foundational requirement for the next generation of smart, energy-efficient connectivity and interaction. The Real-World Challenges Of Deploying SLMs At The Edge Despite the excitement, several hurdles still need to be addressed before SLMs at the edge can reach mainstream adoption: • Model Compatibility And Scaling: Not all models can be easily pruned or quantized for edge deployment. Choosing the right architecture—and understanding trade-offs between size, latency and accuracy—is critical. • Ecosystem Fragmentation: Many edge hardware platforms are siloed with proprietary software development kits (SDKs). This lack of standardization increases complexity for developers and slows adoption. • Security And Update Infrastructure: Deploying and managing models on edge devices over time—e.g., via over-the-air (OTA) updates—requires robust, secure infrastructure. Democratizing Intelligence—And Sustainability—One Device At A Time Perhaps the most exciting outcome of the SLM revolution is that it levels the playing field. By removing the infrastructure barriers traditionally associated with AI, it allows startups, original equipment manufacturers (OEMs) and makers to embed meaningful intelligence in nearly any device. With tens of billions of connected devices already in use—spanning everything from thermostats to factory robots—the opportunity is vast. And local inference is more than just responsive—it's dramatically more energy efficient than cloud-based alternatives, supporting greener AI deployment strategies. AI doesn't need to be massive to be meaningful. Sometimes the most powerful intelligence is also the most efficient. As SLMs continue to evolve and hardware support becomes more ubiquitous, the smart edge will move from possibility to default. In the process, we'll unlock new classes of real-time, personalized and sustainable AI experiences—delivered not from distant data centers, but from the device in your hand, pocket or factory floor. Forbes Technology Council is an invitation-only community for world-class CIOs, CTOs and technology executives. Do I qualify?
Yahoo
24-06-2025
- Business
- Yahoo
Ceva Launches MotionEngine™ Hex: Bringing Precise, Touch-Free, Spatial Control to Smart TV, Gaming, and IoT Interfaces
MotionEngine Hex software fuses UWB and motion sensor data to deliver 6-degree-of-freedom (6-DOF) motion tracking and intuitive control, enabling new interaction paradigms for electronic displays ROCKVILLE, Md., June 24, 2025 /PRNewswire/ -- Ceva, Inc. (NASDAQ: CEVA), the leading licensor of silicon and software IP that enables Smart Edge devices to connect, sense and infer data more reliably and efficiently, today introduced MotionEngine™ Hex, a next-generation motion control software solution that enables precise, natural interaction with Smart TVs and connected displays. By combining ultra-wideband (UWB) positioning with inertial measurement unit (IMU) orientation sensing, MotionEngine Hex delivers true 6-degree-of-freedom (6-DOF) tracking – allowing users to control on-screen content with touchscreen-like pointing accuracy and spatial gestures, without ever touching the screen. Designed for OEMs and developers seeking to push the boundaries of user interaction, MotionEngine Hex is a robust, low-latency software stack that enables precise 3D position and orientation tracking in real time. The result is a direct, touchscreen-like experience that enhances usability and unlocks new interaction modes where the edge of the screen is no longer the limit. This direct pointing experience is ideal for navigating modern smart TV interfaces, PC monitors, commercial displays, gaming, and even controlling smart home devices. "We designed MotionEngine Hex to feel like an extension of your hand," said Chad Lucien, vice president and general manager of the sensor and audio business unit at Ceva. "It's precise, intuitive, and opens up entirely new ways to interact with content on digital displays. It's a powerful way for device makers to differentiate their products in a crowded market while delivering a premium, next-gen user experience that consumers will immediately appreciate." MotionEngine Hex is built on the Ceva MotionEngine software which has been in production for more than 15 years and is deployed in more than 150 million devices. Technical Highlights 6-DOF Sensor Fusion Engine: MotionEngine Hex integrates data from a 3-axis accelerometer, 3-axis gyroscope, and UWB-based position sensors to compute full 6-DOF pose (position + orientation) with high temporal resolution and spatial accuracy. Absolute Pointing: Unlike relative motion systems, MotionEngine Hex provides absolute cursor positioning based on real-world spatial coordinates, enabling intuitive interactions such as direct selection, on and off-screen gestures, and spatial drag-and-drop. Dual Architecture Support: Host-Based: Runs on the host processor (e.g., TV SoC or STB CPU), interfacing with Bluetooth and UWB modules. Embedded: Optimized for integration into Bluetooth SoCs within remote controls, enabling standalone operation with minimal host dependency. Sensor Calibration and Compensation: Includes runtime calibration, drift compensation, and tremor suppression algorithms to ensure consistent performance across environments and users. Low Power, Small Footprint: Designed for embedded systems with constrained resources, MotionEngine Hex operates efficiently on low-power MCUs and DSPs, making it ideal for battery-powered remotes and handheld devices. MotionEngine Hex is available now and will be demonstrated at Sensors Converge Conference, June 25 - 26, 2025 at the Santa Clara Convention Center, Santa Clara, CA. For more on MotionEngine Hex and Ceva's motion-sensing technologies, visit About Ceva, 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 smartedge products. From Bluetooth, Wi-Fi, UWB and 5G platform IP for ubiquitous, robust communications, to scalable Edge AI NPU IPs, sensor fusion processors and embedded application software that make devices smarter, we have the broadest portfolio of IP to connect, sense and infer data more reliably and efficiently. We deliver differentiated solutions that combine outstanding performance at ultra-low power within a very small silicon footprint. Our goal is simple – to deliver the silicon and software IP to enable a smarter, safer, and more interconnected world. This philosophy is in practice today, with Ceva powering more than 19 billion of the world's most innovative smart edge products from AI-infused smartwatches, IoT devices and wearables to autonomous vehicles and 5G mobile networks. Our headquarters are in Rockville, Maryland with a global customer base supported by operations worldwide. Our employees are among the leading experts in their areas of specialty, consistently solving the most complex design challenges, enabling our customers to bring innovative smart edge products to market. Ceva: Powering the Smart Edge™ Visit us at and follow us on LinkedIn, X, YouTube, Facebook, and Instagram. View original content to download multimedia: SOURCE Ceva, Inc. Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Yahoo
04-03-2025
- Business
- Yahoo
Ceva Collaborates with Arm and SynaXG to Redefine Energy Efficient 5G NR Processing for Sustainable LEO Satellites and 5G-Advanced Wireless Infrastructure
Leveraging Arm Neoverse CPUs, Ceva's Hardware Accelerated 5G NR Baseband Platform and SynaXG's 5G NR RAN Expertise, customized baseband processing solution delivers 10X better efficiency than traditional solutions and 20X more efficient than FPGA-based alternatives BARCELONA, Spain, March 4, 2025 /PRNewswire/ -- MWC25 -- Ceva, Inc. (NASDAQ: CEVA), the leading licensor of silicon and software IP that enables Smart Edge devices to connect, sense and infer data more reliably and efficiently, announced today a strategic collaboration with Arm and SynaXG to offer a customized 5G-Advanced solution that delivers unparalleled energy efficiency for 5G NR processing in wireless network equipment and satellites. This solution will also serve to offer existing and new players in the wireless infrastructure markets a low-risk path to address 5G-Advanced and the evolution towards 6G. Built with Arm® Neoverse™ N2 CPUs, the Ceva-PentaG-RAN platform and SynaXG's carrier-grade RAN software, this customized, highly-integrated solution redefines power efficiency for 5G infrastructure applications. For baseband processing, it delivers 10X better efficiency than traditional solutions and 20X more efficient than FPGA-based alternatives that are used today*. This remarkable improvement paves the way for truly sustainable LEO satellites and terrestrial 5G-Advanced infrastructure components that are more compact, lighter, require less power to operate and ultimately have a reduced environmental impact. Panch Chandrasekaran, Director of Segment Marketing, Infrastructure Line of Business, Arm, stated: "Arm Neoverse was designed to help Arm Total Design partners like Ceva build innovative new solutions that deliver transformative levels of workload-specific performance and efficiency. "This collaboration with Ceva and SynaXG sets a new benchmark for energy-efficient processing with the potential to make a significant impact on wireless infrastructure and 5G-advanced solutions." Mantosh Malhotra, Chief Business Officer, SynaXG, added: "By integrating our comprehensive 5G NR software suite, which includes our carrier-grade 5G PHY and stack solutions, with the high-performance, power-efficiency capabilities of Arm Neoverse and Ceva's innovative platforms, we're delivering a transformative solution that sets a new standard for efficiency and sustainability in 5G-Advanced infrastructure. This strategic partnership underscores our commitment to driving the evolution of 5G and empowering the development of environmentally friendly, next-generation wireless networks." Elad Baram, Product Marketing Director, Mobile Broadband Business Unit, Ceva, concluded: "As the wireless industry evolves, the convergence of 5G-Advanced and satellite communications requires a new generation of energy-efficient systems that can power 5G-capable satellite networks and terrestrial equipment. In collaboration with Arm and SynaXG, we've achieved a major breakthrough in reducing power consumption for 5G workloads, enabling the development of compact, lightweight, and environmentally friendly infrastructure. This innovation is poised to revolutionize the form factor of wireless network equipment, enabling a new era of sustainable and connected 5G solutions." About the Solution This collaborative 5G-Advanced solution combines carrier-grade software from SynaXG working seamlessly on power-efficient hardware provided by Arm and Ceva to deliver unparalleled energy efficiency for 5G NR processing. Ceva contributes its PentaG-RAN baseband processing platform, which includes Ceva vector and scalar DSP cores, optimized fixed-function hardware accelerators, and proven, optimized software modules. Arm provides the Neoverse N2 core, its first Armv9 infrastructure CPU, which delivers industry-leading performance-per-watt efficiency. SynaXG's software stack, runs on top of the Arm-Ceva Hardware, to deliver a full 5G baseband solution suitable for even the most challenging infrastructure use cases. PentaG-RAN provides a groundbreaking platform for a complete L1 PHY (physical layer 1) solution with optimal hardware/software partitioning, incorporating powerful vector DSPs, PHY control DSPs, flexible 5G hardware accelerators and other specialized components required for modem processing chains. It delivers up to 20X savings in power and area compared to available FPGA and commercial-off-the-shelf (COTS) CPU based alternatives. The Ceva PentaG-RAN platform is RF front-end agnostic, ensuring it can be utilized for the development of 5G-Advanced systems targeting mmWave and sub-6-GHz networks. For more information, visit *Additional performance data available upon request. About Ceva, Inc. 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. From wireless connectivity IPs (Bluetooth, Wi-Fi, UWB and 5G platform IP), to scalable Edge AI NPU IPs and sensor fusion solutions, we have the broadest portfolio of IP to connect, sense and infer data more reliably and efficiently. We deliver differentiated solutions that combine outstanding performance at ultra-low power within a very small silicon footprint. Our goal is simple – to deliver the silicon and software IP to enable a smarter, safer, and more interconnected world. This philosophy is in practice today, with Ceva powering more than 19 billion of the world's most innovative smart edge products from AI-infused smartwatches, IoT devices and wearables to autonomous vehicles and 5G mobile networks. Our headquarters are in Rockville, Maryland with a global customer base supported by operations worldwide. Our employees are among the leading experts in their areas of specialty, consistently solving the most complex design challenges, enabling our customers to bring innovative smart edge products to market. Ceva: Powering the Smart Edge™ Visit us at and follow us on LinkedIn, X, YouTube, Facebook, and Instagram. Logo: View original content: SOURCE Ceva, Inc. Sign in to access your portfolio
