RK3588

Tutorial: Debugging XDMA on ARM Devices (RK3588) – Continued

by
Tutorial: Debugging XDMA on ARM Devices (RK3588) - Continued

Click the blue text above to follow us Preface On AMD’s official Q&A platform, the official staff directly responded that they do not support users compiling and testing XDMA drivers on ARM. https://adaptivesupport.amd.com/s/question/0D52E00006hpPyySAE/xdma-device-driver-ar65444-fix-for-arm?language=en_US This case uses the latest version of the XDMA driver. Additionally, during the actual operation, I used several earlier versions of the … Read more

Issues Encountered When Compiling boot.img for RK3588

by
Issues Encountered When Compiling boot.img for RK3588

The kernel version from Rockchip can be downloaded from GitHub at the link: https://github.com/rockchip-linux/kernel. There is also a complete SDK development environment available directly from the manufacturer, including uboot, buildroot, kernel, etc. Additionally, there are some open-source projects from openEuler, which are quite varied and chaotic. For version 5.10, there are multiple sub-versions, and the … Read more

PAS-2310 Embedded AI Vision Controller: Ushering in a New Era of Industrial Intelligence

by
PAS-2310 Embedded AI Vision Controller: Ushering in a New Era of Industrial Intelligence

In the context of accelerating industrial automation and intelligence, Zhiwei Industrial has launched the PAS-2310 ARM Embedded AI Vision Controller, specifically designed for embedded vision inspection scenarios. This product is based on the high-performance, low-power RK3588 platform, integrating powerful AI computing capabilities, rich interfaces, and industrial-grade reliability, fully supporting various industrial vision systems to achieve … Read more

Tutorial: End-to-End Communication of ARM Device (RK3588) with XDMA

by
Tutorial: End-to-End Communication of ARM Device (RK3588) with XDMA

The Xilinx DMA/Bridge Subsystem for PCI Express (PCIE) IP (XDMA) significantly reduces the difficulty for FPGA developers in using the PCIE interface. By implementing a simple BD design, FPGA-side logic design can be achieved, and with open drivers and example code, developers can quickly establish end-to-end communication over PCIE.Currently, Xilinx has released drivers for XDMA … Read more

Application Case: Domestic RK3588 High-Performance Edge Computing Industrial Computer Assists Enterprises in Achieving Full-Link Intelligent Upgrade of Industrial Data

by
Application Case: Domestic RK3588 High-Performance Edge Computing Industrial Computer Assists Enterprises in Achieving Full-Link Intelligent Upgrade of Industrial Data

Application Case In a smart manufacturing enterprise’s production line upgrade project, faced with the stringent demands of processing a large amount of equipment status data daily and connecting multiple heterogeneous terminals, traditional industrial computers struggle to support real-time decision-making due to computational bottlenecks and communication delays.The Inconsi NIS-5130 industrial computer, with its edge computing architecture … Read more

Deploying Qwen 3.0 on RK3588 – Continuation

by
Deploying Qwen 3.0 on RK3588 - Continuation

Qwen3 is deployed on rk3588, defaulting to thinking mode, which can be switched to non-thinking mode by adding /no_think to the user input. How to change the default mode to non-thinking on rk3588? That is, setting enable_thinking=False will also take effect on rk3588. Let’s take a look at Qwen3‘s chat_template.Tokenizer_config.json is located in "chat_template": "{%- … Read more

Deploying Qwen 3.0 Based on RK3588

by
Deploying Qwen 3.0 Based on RK3588

Requires the following versionRKLLM https://github.com/airockchip/rknn-llm/tree/release-v1.2.1b1 Install theRKLLM-Toolkit for this version, otherwise the model conversion may fail. Download the model file, taking Qwen3-0.6B as an example https://www.modelscope.cn/models/Qwen/Qwen3-0.6B Modify rknn-llm/examples/DeepSeek-R1-Distill-Qwen-1.5B_Demo/export/export_rkllm.py Changemodelpath to the downloadedQwen3 directory modelpath = ‘/home/andy/rkllm/Qwen3-0.6B’ Executepython export_rkllm.py to convert to therkllm supported model format. INFO: rkllm-toolkit version: 1.2.1b1WARNING: Cuda device not available! switch to … Read more

Board-to-Board Connector Method | Core Board Z-3588

by
Board-to-Board Connector Method | Core Board Z-3588

The Z-3588 is the first core board based on the RK3588 platform from LIONTRON, featuring ultra-high performance, strong computing power, and low power consumption. This core board utilizes a board-to-board connector interface, supporting the expansion of 2 CAN channels, 2 Gigabit Ethernet, USB 3.0, and SATA 3.0 high-performance interfaces through the baseboard, meeting the needs … Read more

Using the RK3588 Chip NPU: Compiling YOLOv8-Pose C Demo in Windows 11 Docker and Running on Development Board

by
Using the RK3588 Chip NPU: Compiling YOLOv8-Pose C Demo in Windows 11 Docker and Running on Development Board

The Objective of This Article This article will compile the YOLOv8-Pose C Demo in the RKNN Docker environment and deploy it to the RK3588 development board using the adb tool. Development Environment Description Host System: Windows 11 Target Device: Android development board equipped with the RK3588 chip Core Tools: Docker image containing rknn-toolkit2, rknn_model_zoo, and … Read more

Industry Trends: Security Monitoring Main Chip (SoC) Series – Rockchip RK3588

by
Industry Trends: Security Monitoring Main Chip (SoC) Series - Rockchip RK3588

The security industry has emerged in response to the modern society’s demand for safety. With the reform and innovation of video surveillance technology, the industry has gone through four stages: analog monitoring, digital monitoring, network high-definition monitoring, and intelligent monitoring. Each breakthrough in these stages has been led by innovations in upstream technology.In security monitoring … Read more