Search Results for "computing"

ncnn is a high-performance neural network inference computing framework designed specifically for mobile platforms. It brings artificial intelligence right at your fingertips with no third-party dependencies, and speeds faster than all other known open source frameworks for mobile phone cpu. ncnn allows developers to easily deploy deep learning algorithm models to the mobile platform and create intelligent APPs.

...MNN Workbench could be downloaded from MNN's homepage, which provides pretrained models, visualized training tools, and one-click deployment of models to devices. Android platform, core so size is about 400KB, OpenCL so is about 400KB, Vulkan so is about 400KB. Supports hybrid computing on multiple devices. Currently supports CPU and GPU.

Agency Agents is an open-source collection of specialized AI agent personas designed to function like a complete virtual agency spanning engineering, design, marketing, product, project management, testing, support, spatial computing, and other specialized roles. Rather than providing generic prompts, the project organizes each agent as a structured expert profile with personality traits, mission, workflow, deliverables, examples, and success metrics so that each one feels more like a reusable operational role than a one-off instruction. The repository is built for people who want role-based AI collaboration, whether that means using the agents directly inside Claude Code, adapting them as references, or converting them for use in other agentic tools such as Cursor, Aider, Windsurf, Gemini CLI, and OpenCode.

...The framework focuses on making it easier to transform trained AI models into production-ready applications that can run efficiently on desktops, mobile devices, servers, and edge computing hardware. Developers can use visual workflows to design and configure AI processing pipelines by connecting modular nodes that represent different stages of the inference process. The system supports multiple inference engines and hardware accelerators, allowing the same AI workflow to run on different platforms without significant modifications. nndeploy also includes performance optimization techniques such as parallel execution, memory reuse, and hardware-accelerated operations to improve inference speed.

Mobile AI Compute Engine (or MACE for short) is a deep learning inference framework optimized for mobile heterogeneous computing on Android, iOS, Linux and Windows devices. Runtime is optimized with NEON, OpenCL and Hexagon, and Winograd algorithm is introduced to speed up convolution operations. The initialization is also optimized to be faster. Chip-dependent power options like big.LITTLE scheduling, Adreno GPU hints are included as advanced APIs. UI responsiveness guarantee is sometimes obligatory when running a model. ...