Search Results for "vulkan"

qvac-fabric-llm.cpp is a cross-platform large language model inference and fine-tuning engine built as an advanced fork of llama.cpp, designed to run efficiently across desktops, mobile devices, and heterogeneous GPU environments. The project focuses on removing hardware limitations traditionally associated with LLM deployment by enabling support for a wide range of backends, including Vulkan, Metal, CUDA, and CPU, making it accessible on devices ranging from smartphones to enterprise servers. It introduces native LoRA fine-tuning capabilities that can be executed directly on consumer hardware, allowing developers to train and adapt models locally without relying on cloud infrastructure. A key innovation is its support for BitNet ternary quantized models, enabling highly efficient inference and training even on resource-constrained systems.

...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.

OGRE (Object-Oriented Graphics Rendering Engine) is a scene-oriented, flexible 3D engine written in C++ designed to make it easier and more intuitive for developers to produce games and demos utilizing 3D hardware. The class library abstracts all the details of using the underlying system libraries like Direct3D and OpenGL and provides an interface based on world objects and other intuitive classes. We consider the results of our GL3Plus RenderSystem as the gold standard. The respective...

This is a mirror of the LLGL GitHub repository. See https://github.com/LukasBanana/LLGL for more details.

...Up to 16K texture painting is seamless using a high-end graphics card. Ray-traced baking, painting effects and viewport rendering feature running on Direct3D12 and Vulkan are in progress. ArmorPaint is powered by an in-house 3D rendering engine to achieve the best painting experience.

...Rio uses WGPU, which is an implementation of WebGPU for use outside of a browser and as backend for firefox’s WebGPU implementation. WebGPU allows for more efficient usage of modern GPU’s than WebGL. Applications using WPGU run natively on Vulkan, Metal, DirectX 11/12, and OpenGL ES; and browsers via WebAssembly on WebGPU and WebGL2.

This is an unofficial Google Cardboard Unity SDK, implemented from new Google Cardboard open source project. This project is released, it is production-ready now. OpenGL ES 3.0 and Metal(iOS) and Vulkan(Android) Support (as well as OpenGL ES 2.0). Ability to set cardboard profile in script. Switch between vr and no-vr mode (magic window).

...And it’s free to use, even for com­mer­cial pur­poses. Among Mag­num es­sen­tials is a UTF-8-aware OS, filesys­tem and con­sole ab­strac­tion, a ver­sat­ile vec­tor math lib­rary and a slim C++11 wrap­per of Vulkan and OpenGL API fam­il­ies. Build on top of that or opt-in for more. Shaders and prim­it­ives for fast pro­to­typ­ing, al­gorithms, de­bug­ging and auto­mat­ic test­ing, as­set man­age­ment, in­teg­ra­tion with pop­u­lar win­dow­ing toolkits and a UI lib­rary. Everything fits to­geth­er but you still have a choice. There’s al­ways more than one way to do things.