artificial intelligence (AI) News - Page 18 of 121 - CNX Software

July 15, 2024July 15, 2024 by Jean-Luc Aufranc (CNXSoft) - 7 Comments

Rockchip RKLLM toolkit released for NPU-accelerated large language models on RK3588, RK3588S, RK3576 SoCs

Rockchip RKLLM toolkit (also known as rknn-llm) is a software stack used to deploy generative AI models to Rockchip RK3588, RK3588S, or RK3576 SoC using the built-in NPU with 6 TOPS of AI performance. We previously tested LLM’s on Rockchip RK3588 SBC using the Mali G610 GPU, and expected NPU support to come soon. A post on X by Orange Pi notified us that the RKLLM software stack had been released and worked on Orange Pi 5 family of single board computers and the Orange Pi CM5 system-on-module. The Orange Pi 5 Pro‘s user manual provides instructions on page 433 of the 616-page document, but Radxa has similar instructions on their wiki explaining how to use RKLLM and deploy LLM to Rockchip RK3588(S) boards. The stable version of the RKNN-LLM was released in May 2024 and currently supports the following models: TinyLLAMA 1.1B Qwen 1.8B Qwen2 0.5B Phi-2 2.7B Phi-3 […]

July 15, 2024July 14, 2024 by Jean-Luc Aufranc (CNXSoft) - 3 Comments

Khadas Mind Graphics NVIDIA RTX 4060 Ti GPU dock for the Mind mini PC is now available for $999

The Khadas Mind Graphics is a dock for the Khadas Mind Raptor Lake mini PC that integrates an NVIDIA Geforce RTX 4060 Ti GPU and enables users to run high-end games, edit videos, design graphics, and experiment with AI while keeping the portability and small size of a mini PC. As we’ve seen in our reviews, mini PCs now match the performance of larger machines in almost all aspects with tools like PassMark Performance showing higher-end models’ CPU, memory bandwidth, and storage in the top 10% or 20% of systems. The exception is 3D graphics performance because integrated GPUs can’t match the performance of higher-end graphics cards. The Khadas Mind Graphics solves that by adding an NVIDIA Geforce RTX 40601 Ti GPU to the Khadas Mind mini PC through its Mind Link connector also bringing out other connectors such as 2.5GbE, USB, SD card, etc… Khadas Mind Graphics specifications: Graphics […]

July 11, 2024July 11, 2024 by Sponsored Post - No Comments

Mixtile Edge AI boxes work with ONVIF cameras to deploy video analytics solutions (Sponsored)

Mixtile Edge AI solution supports ONVIF cameras and leverages object detection, object classification, real-time analysis, and intelligent monitoring to create IoT video analytics applications across the security, transportation, logistics, retail, industry, and agriculture sectors. The hardware is based on the time-tested Mixtile Edge 2 Kit IoT gateway powered by a Rockchip RK3568 SoC with a 1 TOPS NPU and 1080p60 VPU, or Mixtile Blade 3 SBC featuring the more powerful Rockchip RK3588 octa-core SoC with a 6 TOPS AI accelerator and an 8Kp60 VPU. The former can analyze up to 10 streams in real-time, and the latter up to a whopping 40 streams. So the novelty here is on the software side that has been developed by Mixtile and works the following way: The ONVIF cameras transmit video streams to a Mixtile Edge AI Box over the network. The Edge AI Box then runs pre-trained AI models to analyze the […]

July 3, 2024July 3, 2024 by Jean-Luc Aufranc (CNXSoft) - 31 Comments

Banana Pi BPI-M5 Pro low-profile SBC features Rockchip RK3576 octa-core Cortex-A72/A53 AIoT SoC

Banana Pi BPI-M5 Pro, also known as Armsom Sige5, is a low-profile single board computer (SBC) powered by the Rockchip RK3576 octa-core Cortex-A72/A53 SoC for the AIoT market that offers a mid-range offering between Rockchip RK3588 and RK3399 SoCs. The board comes with 16GB LPDDR4X and 128GB eMMC flash by default, offers dual GbE, WiFi 6 and Bluetooth 5.2 connectivity, an M.2 2280 PCIe socket for expansion, HDMI and MIPI DSI display interfaces, two MIPI CSI camera interfaces, a few USB ports, and a 40-pin GPIO header. Banana Pi BPI-M5 Pro specifications: SoC – Rockchip RK3576 CPU 4x Cortex-A72 cores @ 2.2GHz, four Cortex-A53 cores @ 1.8GHz Arm Cortex-M0 MCU at 400MHz GPU – ARM Mali-G52 MC3 GPU with support for OpenGL ES 1.1, 2.0, and 3.2, OpenCL up to 2.0, and Vulkan 1.1 NPU – 6 TOPS (INT8) AI accelerator with support for INT4/INT8/INT16/BF16/TF32 mixed operations. VPU Video Decoder: […]

July 3, 2024 by Debashis Das - No Comments

NXP SAF9000 and SAF9100 Automotive Audio DSP bring AI to car infotainment

NXP AI Audio Proce with SAF9xxx Audio DSPs

NXP has recently launched the SAF9xxx Automotive Audio DSP family, which currently includes SAF9000 and SAF9100 AI audio DSPs. Built around Cadence’s latest generation high-performance Tensilica HiFi 5 DSPs, these new chips not only feature AI and ML capabilities, but also include features like driver’s voice pitches and accent recognition, noise cancellation, voice recognition, emergency siren detection, and more. Additionally, the SAF9000 chip includes a software-defined radio option with up to five integrated tuners (controlled by an integrated Arm Cortex-M7 core) that covers all major global broadcast radio standards, including DAB, HD Radio, DRM, CDR, and AM/FM into a single chip solution. SAF9xxx Automotive Audio DSP specifications DSP – Tensilica HiFi 5 DSPs with dedicated neural network engines Integrated Controller – Arm Cortex-M7 core for tuner and audio control middleware Radio Features (SAF9000 only) Supports AM, FM, DAB, DAB+, DMB, HD Radio, DRM for AM, DRM for FM (DRM+), CDR […]

July 1, 2024July 1, 2024 by Jean-Luc Aufranc (CNXSoft) - 21 Comments

Amlogic S905X5M vs S905X4 – Features and benchmarks comparison

Amlogic S905X5M is an update to the Amlogic S905X4 quad-core Cortex-A55 SoC with a higher 2.5 GHz CPU clock and a new generation Arm G310 CPU that delivers up to close to three times the performance of the Mali-G31 MP2 GPU for more advanced and smoother HDR user interfaces. The S905X5M and S905X4 share the same video decoding capabilities, notably AV1 and H265 up to 4Kp75, but the new S905X5M drops support for H.265 1080p60 video encoding, only keeping H.264 1080p30. One of the new features is the inclusion of an NPU designed specifically for Super Resolution enabling video upscaling with better image quality. You’ll find the differences between the Amlogic S905X5M and S905X5 processors in the comparison table below. The Amlogic S905X5M adds some HDMI 2.1 features that deserve an explanation: QMS (Quick Media Switching) – A source device can instantly switch its content’s resolution or frame rate without […]

June 28, 2024June 28, 2024 by Debashis Das - 2 Comments

Infineon CY8CKIT-062S2-AI PSoC 6 Edge AI evaluation kit features multiple sensors, Arduino headers, Pmod connectors

Infineon CY8CKIT-062S2-AI evaluation kit is a hardware platform built around the PSoC 6 family of MCUs and designed to help developers easily create and test edge AI applications. The dev board features an array of sensors including radar, microphone, magnetometer, IMU, and an air pressure sensor, which make it easy for data collection applications. The board also features Wi-Fi and Bluetooth connectivity and includes an additional expansion header that can be used to connect other modules and sensors. All of these features make this board useful for building a wide range of AI-powered applications, including smart home automation, industrial monitoring, wearables, healthcare devices, and robotics. Previously we have written about similar low-power edge AI modules such as the Digi ConnectCore MP25, the Axiomtek AIE110-XNX, and the Arducam KingKong feel free to check those out if you are interested in such low-power modules. Infineon CY8CKIT-062S2-AI Evaluation Kit specifications: MCU – Infineon […]

June 26, 2024June 26, 2024 by Jean-Luc Aufranc (CNXSoft) - 9 Comments

Pine64 Oz64 RISC-V+Arm SBC to support NuttX RTOS and Debian Linux

Pine64 Oz64 is an upcoming credit card-sized SBC based on the SOPHGO SG2000 RISC-V+Arm(+8051) processor that currently runs NuTTX RTOS, and a Debian Linux image is also in the works. With a name likely inspired by the earlier Pine64 Ox RISC-V SBC, the Oz64 is a more powerful embedded board with 512 MB of DRAM integrated into the SG2000, a microSD card, an eMMC flash module connector, Ethernet port, WiFi 6 and Bluetooth 5.2, a USB 2.0 Type-A host port, and a 26-pin GPIO header. Pine64 Oz64 specifications: SoC – SOPHGO SG2000 Main core – 1 GHz 64-bit RISC-V C906 or Arm Cortex-A53 core (selectable) Minor core – 700 MHz 64-bit RISC-V C906 core Low-power core – 25 to 300 MHz 8051 MCU core with 8KB SRAM NPU – 0.5 TOPS INT8, supports BF16 Integrated 512MB DDR3 (SiP) Storage MicroSD card slot eMMC flash module connector Display – Optional 2-lane […]