👇 Follow our official account and selectStar, to receive the latest insights daily Abstract The NPU (Neural Processing Unit) is a chip designed specifically for neural network computations, excelling in matrix operations and convolution tasks, characterized by low power consumption and high efficiency. It is mainly used for inference tasks on edge devices, such as … Read more
Since the emergence of ChatGPT at the end of 2022, followed by the hundred-model battle in 2023, and the recent releases of GPT-4.5 by OpenAI, Grok3 by xAI, Claude 3.7 Sonnet by Anthropic, and Llama4 by Meta, the iteration speed of large models has been accelerating. In China, there has been a surge in open-source … Read more
Address:https://github.com/NotPunchnox/rkllama RKLLama is an open-source server and client solution designed to run large language models (LLMs) optimized for the Rockchip RK3588 (S) and RK3576 platforms, and to interact with them. Unlike solutions such as Ollama or Llama.cpp, RKLLama fully utilizes the Neural Processing Units (NPU) on these devices, providing an efficient and high-performance solution for … Read more
Course Introduction The emergence of large models like DeepSeek has triggered explosive growth in AI applications, with a continuous rise in edge inference demand. The NPU (Neural Processing Unit), with its excellent AI acceleration capabilities and high energy efficiency, has become a key solution to meet terminal inference needs. Arm Technology’s self-developed ‘Zhou Yi’ NPU … Read more
In the past decade, artificial intelligence (AI) and machine learning (ML) have undergone significant transformations—convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are transitioning to Transformers and generative artificial intelligence (GenAI). This transformation is driven by the industry’s urgent demand for models that are efficient, accurate, context-aware, and capable of handling complex tasks.Initially, AI … Read more
Recently, Qunxin Shining, a member of the Jiachen Project, donated one set of Milk-V Megrez motherboard (including fan) to the leader of the Jiachen Project, receiving 1499 drifting points (see the observation address at the end of the article [2]). This donation is a targeted donation, and the leader of the Jiachen Project will (along … Read more
Click the 🔺 public account above to follow me ✅ Computing power has become a significant bottleneck in the development of AI. To overcome this bottleneck, GPUs and NPUs, as the two main forces, are addressing this issue in different ways. So, how does the NPU accelerate AI from a hardware perspective? What are the … Read more
Since the beginning of 2025, with the maturation of technology and the expansion of application scenarios, the edge AI market has experienced rapid growth. It is predicted that by 2025, the edge computing market will approach $50 billion, becoming an important engine for fostering new business models and optimizing resource allocation. The demand for high-performance, … Read more
1. Hardware Devices (1) RK3399Pro Development Board: This is a development board launched by Rockchip, equipped with NPU (Neural-network Processing Units), supporting 8-bit and 16-bit operations, with a computing performance of up to 3.0 TOPs. Compared to similar NPU chips, its performance is leading by as much as 150%, and it is compatible with various … Read more
Recently, BYD has entered the final phase of depleting its non-intelligent vehicle inventory, soon to initiate equal rights for intelligent driving. The conference had some highlights, especially Bosch’s speech on intelligent driving for traditional vehicles. Today, let’s briefly analyze the intelligent driving chip architectures of two third-party companies. 1. Black Sesame Intelligence: Self-developed NPU Architecture … Read more