As enterprises race to adopt generative AI and bring new services to market, the demands on data center infrastructure have never been greater. Training large language models is one challenge, but delivering LLM-powered real-time services is another. In the latest round of MLPerf industry benchmarks, Inference v4.1, NVIDIA platforms delivered leading performance across all data center tests. The first-ever submission of the upcoming NVIDIA Blackwell platform revealed up to 4x more performance than the NVIDIA H100 Tensor Core GPU on MLPerf's biggest LLM workload, Llama 2 70B, thanks to its use of a second-generation Transformer Engine and FP4 Tensor Cores.

The NVIDIA H200 Tensor Core GPU delivered outstanding results on every benchmark in the data center category - including the latest addition to the benchmark, the Mixtral 8x7B mixture of experts (MoE) LLM, which features a total of 46.7 billion parameters, with 12.9 billion parameters active per token. MoE models have gained popularity as a way to bring more versatility to LLM deployments, as they're capable of answering a wide variety of questions and performing more diverse tasks in a single deployment. They're also more efficient since they only activate a few experts per inference - meaning they deliver results much faster than dense models of a similar size.

While it was keen to show off its earlier released Live Gamer ULTRA 2.1 (GC553G2) USB and Live Gamer 4K 2.1 (GC575) PCIe HDMI 2.1 capture cards which have recently got a big firmware update, giving them 4K144 capture, support for 5.1 multi-channel audio, and support for Windows 11 Dynamic Lighting, AVerMedia had a lot of other new things to show at the Computex 2024 show, including the new Premium Go Series, which includes the world's first Capture Dock, the X'tra Go GC515, the Elite Go GC313Pro and Core Go GC313 GaN charger and capture device, new AVerMedia Streaming Center software, and a couple of NVIDIA Jetson Orin NX-based Box PCs for edge AI.

As said, the new AVerMedia Premium Go Series kicks off with the X'tra Go GC515, which is the world's first Capture Dock for various handheld devices. The Xtra Go GC515 does exactly what you think it does, and that is record 4K30 or 1080p120 footage from a handheld gaming device with just a simple click and without a computer. It is compatible with popular models like Nintendo Switch, Steam Deck, ROG Ally, and probably most other handheld consoles. Of course, since it does not require a PC, it records everything on a microSD card. The Premium Go Series also features GaN chargers with video capture capability, including the Elite Go GC313Pro, a 100 W charger with HDMI 4K60 output, USB-C 1080p60 capture, and an ability to charge multiple device. There is also the Core Go GC313 GaN charger and capture device, which allows users to display their video signal on a monitor at up to 4K60 via HDMI while the device is charging.

AVerMedia, a pioneer in digital multimedia, is thrilled to announce its participation in COMPUTEX 2024, taking place from June 4-7, 2024, at the Taipei Nangang Exhibition Center. Visit us at booth L1309a (Hall 1, 4F) to explore our latest innovations designed to empower creators, streamers, and professionals in the digital age.

Under the theme "Create and Connect", AVerMedia will showcase a range of groundbreaking solutions. These include the new Premium Go Series for handheld device charging and capturing, an award-winning streaming software that integrates all essentials for diverse streaming applications, advanced solutions for next-gen gameplay streaming, a comprehensive series of video conference tools to enhance remote communication and collaboration, and innovative embedded solutions that push the boundaries of what's possible in the digital multimedia landscape.

PNY Technologies, a pioneer in high-performance computing, proudly announces the launch of a groundbreaking developer platform, uniting the formidable capabilities of NVIDIA IGX Orin, NVIDIA Holoscan and Magic Leap 2. This visionary kit empowers software and technology vendors to pioneer cutting-edge solutions in healthcare and other industries, redefining the boundaries of innovation.

Key Features of the NVIDIA IGX + Magic Leap 2 XR Bundle:

• Zero Physical World Latency for Mission-Critical Applications: Ensure zero physical world latency for mission-critical applications, offering unparalleled precision and real-time data processing.
• AI Inference and Local Computation: Leverage NVIDIA IGX Orin for AI inference and local computation of complex models, using NVIDIA Holoscan as its real-time multimodal AI sensor processing platform and NVIDIA Metropolis software to offer XR use cases.
• Ultra-Precise Augmented Reality Interface: Magic Leap 2 delivers an ultra-precise augmented reality interface for accurate and immersive experiences.

The global edge artificial intelligence (AI) market is booming, which has accelerated the urgent demand for reliable, high-performance, and highly flexible edge AI inference devices. Aetina, a leading global edge AI solution provider, announces the release of its cutting-edge fanless versatile expansion edge AI systems - the AIE-PN33/43 series and AIE-PO23/33 series. These innovative systems are powered by NVIDIA Jetson Orin NX and Orin Nano modules, offering outstanding AI computing performance of up to 100 TOPS and 40 TOPS respectively, along with flexible I/O interface options. Designed to seamlessly handle the connectivity and real-time data processing needs of various sensors and devices at the edge, these solutions help empower industries worldwide to efficiently deploy an extensive range of AI applications.

According to Statista's 'Number of IoT connected devices worldwide 2019-2030' report, the number of Internet of Things (IoT) devices worldwide is forecasted to exceed 29 billion by 2030. In response to the growing number of IoT devices and the diverse I/O and storage needs of different AI applications, Aetina has unveiled a range of fanless edge AI systems. This lineup includes the AIE-PN33/43-2PSE and AIE-PN33/43-4PSE, boasting 2 or 4 sets of PSE ports respectively; the AIE-PN33/43-6USB and AIE-PO23/33-6USB, each integrating 6 sets of USB ports; and the AIE-PN33/43-3M and AIE-PO23/33-3M, equipped with 3 sets of M.2 M-Key slots. Users can choose the most suitable product model based on their specific AI application requirements, whether it involves addressing wiring challenges in wide-ranging environments like ports or traffic roadside monitoring, fulfilling multi-sensor connectivity needs for smart factory defect detection or automated production lines, or expanding storage capacity for real-time image recognition tasks. These solutions are poised to accelerate the deployment of advanced AI intelligence applications across diverse industries.

Leading provider of embedded PC solutions, AAEON, is delighted to announce the official launch of two new additions to its rich line of embedded AI systems, the BOXER-8653AI and BOXER-8623AI, which are powered by the NVIDIA Jetson Orin NX and Jetson Orin Nano, respectively. Measuring just 180 mm x 136 mm x 75 mm, both systems are compact and easily wall-mounted for discreet deployment, which AAEON indicate make them ideal for use in both indoor and outdoor settings such as factories and parking lots. Adding to this is the systems' environmental resilience, with the BOXER-8653AI sporting a wide -15°C to 60°C temperature tolerance and the BOXER-8623AI able to operate between -15°C and 65°C, with both supporting a 12 V ~ 24 V power input range via a 2-pin terminal block.

The BOXER-8653AI benefits from the NVIDIA Jetson Orin NX module, offering up to 70 TOPS of AI inference performance for applications that require extremely fast analysis of vast quantities of data. Meanwhile, the BOXER-8623AI utilizes the more efficient, yet still powerful NVIDIA Jetson Orin Nano module, capable of up to 40 TOPS. Both systems consequently make use of the 1024-core NVIDIA Ampere architecture GPU with 32 Tensor Cores.

ZOTAC TECHNOLOGY, a global manufacturer focused on innovation, launches the world's first Mini PC featuring the AirJet Solid-State Active Cooling system, as well as a lineup of ARM-based, lightweight edge computing platforms based on the NVIDIA Jetson system on module (SoM).

ZBOX PI430AJ WITH AIRJET, THE WORLD'S FIRST SOLID-STATE ACTIVE-COOLED MINI-PC
First debuted at COMPUTEX 2023, the ZBOX PI430AJ with AirJet is the first product of its kind to feature revolutionary Solid-State Active Cooling technology. With each unit featuring two AirJet Mini Modules by Frore Systems, these thin, silent modules are capable of removing significant heat through rapid airflow, raising the ZBOX PI430AJ's thermal ceiling without compromising its form factor. Taking advantage of the newfound possibilities enabled by the AirJet, the ZBOX PI430AJ is equipped with an Intel Core i3 processor, 8 GB LPDDR5 memory, M.2 SSD storage slot, and more - all within a system the size of a deck of cards.

Aetina launches its new fanless edge AI systems powered by NVIDIA Jetson Orin system-on-modules (SoMs), including the NVIDIA Jetson AGX Orin, Orin NX, and Orin Nano. These embedded box PCs are designed in a compact enclosure with a heat sink for efficient cooling. The heat sink reduces maintenance efforts for system owners after deployment. The new fanless systems have an operating temperature range of -25°C to +55°C, making them suitable for AI-powered application development across different verticals.

NVIDIA Jetson Orin NX and Orin Nano-Based Fanless Systems
AIE-CN31/41, AIE-CO21/31, AIE-PN32/42, and AIE-PO22/32 are Aetina's latest fanless system models built with an NVIDIA Jetson Orin NX or Orin Nano SoM. Featuring necessary M.2 expansion slots and I/O ports in a small-sized form factor, these systems enable easy system integration for space-limited applications. With low power consumption, the fanless system models can efficiently handle most AI inference tasks, making them ideal for AI projects that involve mass device deployment in different locations.

China electric vehicle maker XPENG Motors has announced its new G6 coupe SUV—featuring an NVIDIA-powered intelligent advanced driver assistance system—is now available to the China market. The G6 is XPENG's first model featuring the company's proprietary Smart Electric Platform Architecture (SEPA) 2.0, which aims to reduce development and manufacturing costs and shorten R&D cycles since the modular architecture will be compatible with future models.

The electric SUV also features the XPENG Navigation Guided Pilot (XNGP), a full scenario-based intelligent assisted driving system. It's powered by the cutting-edge NVIDIA DRIVE Orin compute and XPENG's full-stack software developed in-house. The XNGP system first made its debut in the EV maker's flagship G9 SUV, touting a safe, reliable, advanced driving experience behind the wheel.

ASUS IoT, the global AIoT solution provider, today announced PE1100N, a unmatched, ultra-compact computer for AI inferencing at the edge, and based on the next-generation and world-leading NVIDIA Jetson Orin series. It features a fanless design for quiet operation, rich industrial connectivity for serious flexibility and supports a wide range of power inputs and operating temperatures for maximum versatility and durability.

With the powerful Jetson platform, featuring an efficient Arm processor and embedded NVIDIA GPU, PE1100N delivers energy-efficient computing with powerful AI-inferencing capabilities, making it ideal for diverse, scalable edge AI applications in smart city, transportation, manufacturing and more - including traffic analysis, people-tracking, counting and surveillance. Also, PE1100N's compact size and anti-vibration design make it especially ideal for smart manufacturing solutions, such as automated guided vehicle (AGVs), autonomous mobile robots (AMRs), AI-powered automated optical inspection (AOI) and robotics applications - accelerating time to market for AI applications.

Aetina teams up with CVEDIA to launch advanced AI-powered video analytics solutions for enhanced public safety, smarter cities and safer traffic networks. The solutions involve Aetina's embedded computers built with the latest NVIDIA Jetson Orin system-on-modules (SoMs) and CVEDIA's synthetic AI models, enabling low-latency object and human motion detections at the edge. By adopting AI-enabled video analytics, security companies and system integrators can optimize operations and enhance security measures. During ISC West 2023, Aetina and CVEDIA will showcase the solutions to demonstrate how they leverage deep learning to accurately detect, track, and analyze objects and events from videos, enabling businesses to quickly generate insights and improve their decision-making processes.

Aetina's embedded computers that support the NVIDIA Jetson AGX Orin, Orin NX, or Orin Nano SoMs are designed for the creation of different types of vertical AI. The embedded computers provide the computing power for CVEDIA's AI solutions to run real-time inference processes; they are also compatible with any kind of camera to receive high-resolution videos for the analytics tasks.

Aetina Corporation, a leading provider of AI solutions for the creations of different types of vertical AI, will showcase its new embedded computers, AI inference platforms, GPUs, AI accelerators, and edge devices management software at upcoming Embedded World 2023. Aetina provides different types of form factors based on GPUs or ASICs, such as MXMs, graphic cards, and edge computing systems. The MXMs that are powered by NVIDIA Ampere architecture-based GPU offer extra computing power to existing AI systems, ensuring low-latency data analytics tasks. The MXMs and systems that are built with ASICs, on the other hand, are ideal for the creation of any specific applications or AI systems that involve multi-inference processes.

As an Elite member of the NVIDIA Partner Network, Aetina offers a variety of edge computing systems and platforms powered by the NVIDIA Jetson edge AI and robotics platform. Aetina's newly released embedded computers are built with the Jetson Orin series SoMs—Jetson AGX Orin, Jetson Orin NX, and Jetson Orin Nano ; these small-sized systems and platforms, supporting different peripherals, can be easily integrated into larger AI-powered systems while also being able to function as a standalone AI computer.

AAEON, an industry leading developer of edge computing platforms, is happy to announce that it has joined the Azure Certified Device program, ensuring customers get IoT solutions up and running quickly with hardware and software that has been pre-tested and verified to work with Azure IoT. This certification assures that AAEON's new NVIDIA Jetson AGX Orin -powered BOXER-8641AI has been tested for functionality and interoperability, ensuring that it has used the Microsoft reference configuration to become one of the market's first Azure-certified NVIDIA Jetson Orin devices.

This announcement illustrates AAEON's continued innovation in the edge AI space, as the BOXER-8641AI has been validated to work with Azure and the latest versions of IoT Edge. Such a certification gives AAEON customers confidence that when choosing the BOXER-8641AI for their application, it is fully IoT Edge compatible.

NVIDIA today introduced the NVIDIA IGX platform for high-precision edge AI, bringing advanced security and proactive safety to sensitive industries such as manufacturing, logistics and healthcare. In the past, such industries required costly solutions custom built for specific use cases, but the IGX platform is easily programmable and configurable to suit different needs.

As the platform for safe, secure autonomous systems, IGX improves human-machine collaboration. For manufacturing and logistics, IGX provides an additional layer of safety in highly regulated physical-world factories and warehouses. For medical edge AI use cases, IGX delivers secure, low-latency AI inference to address the clinical demand for instantaneous insights from a range of instruments and sensors for medical procedures, such as robotic-assisted surgery and patient monitoring.

NVIDIA today expanded the NVIDIA Jetson lineup with the launch of new Jetson Orin Nano system-on-modules that deliver up to 80x the performance over the prior generation, setting a new standard for entry-level edge AI and robotics. For the first time, the NVIDIA Jetson family spans six Orin-based production modules to support a full range of edge AI and robotics applications. This includes the Orin Nano—which delivers up to 40 trillion operations per second (TOPS) of AI performance in the smallest Jetson form factor—up to the AGX Orin, delivering 275 TOPS for advanced autonomous machines.

Jetson Orin features an NVIDIA Ampere architecture GPU, Arm-based CPUs, next-generation deep learning and vision accelerators, high-speed interfaces, fast memory bandwidth and multimodal sensor support. This performance and versatility empower more customers to commercialize products that once seemed impossible, from engineers deploying edge AI applications to Robotics Operating System (ROS) developers building next-generation intelligent machines.

Bringing new AI and robotics applications and products to market, or supporting existing ones, can be challenging for developers and enterprises. The NVIDIA Jetson AGX Orin 32 GB production module—available now—is here to help. Nearly three dozen technology providers in the NVIDIA Partner Network worldwide are offering commercially available products powered by the new module, which provides up to a 6x performance leap over the previous generation.

With a wide range of offerings from Jetson partners, developers can build and deploy feature-packed Orin-powered systems sporting cameras, sensors, software and connectivity suited for edge AI, robotics, AIoT and embedded applications. Production-ready systems with options for peripherals enable customers to tackle challenges in industries from manufacturing, retail and construction to agriculture, logistics, healthcare, smart cities, last-mile delivery and more.

NVIDIA today introduced NVIDIA DRIVE AGX Orin, a highly advanced software-defined platform for autonomous vehicles and robots. The platform is powered by a new system-on-a-chip (SoC) called Orin, which consists of 17 billion transistors and is the result of four years of R&D investment. The Orin SoC integrates NVIDIA's next-generation GPU architecture and Arm Hercules CPU cores, as well as new deep learning and computer vision accelerators that, in aggregate, deliver 200 trillion operations per second—nearly 7x the performance of NVIDIA's previous generation Xavier SoC.

Orin is designed to handle the large number of applications and deep neural networks that run simultaneously in autonomous vehicles and robots, while achieving systematic safety standards such as ISO 26262 ASIL-D. Built as a software-defined platform, DRIVE AGX Orin is developed to enable architecturally compatible platforms that scale from a Level 2 to full self-driving Level 5 vehicle, enabling OEMs to develop large-scale and complex families of software products. Since both Orin and Xavier are programmable through open CUDA and TensorRT APIs and libraries, developers can leverage their investments across multiple product generations.