Search Results for "webgpu"

Chat with LLM like Vicuna totally in your browser with WebGPU, safely, privately, and with no server. Powered By web-llm. To use this app, you need a browser that supports WebGPU, such as Chrome 113 or Chrome Canary. Chrome versions ≤ 112 are not supported. You will need a GPU with about 6.4GB of memory. If your GPU has less memory, the app will still run, but the response time will be slower. The first time you use the app, you will need to download the model. For the Vicuna-7b model that we...

wgpu is a safe and portable graphics library for Rust based on the WebGPU API. It is suitable for general purpose graphics and compute on the GPU. Applications using wgpu run natively on Vulkan, Metal, DirectX 11/12, and OpenGL ES; and browsers via WebAssembly on WebGPU and WebGL2. Angle is a translation layer from GLES to other backends, developed by Google. We support running our GLES3 backend over it in order to reach platforms with GLES2 or DX11 support, which aren't accessible otherwise...

Easy-to-use headless React Hooks to run LLMs in the browser with WebGPU. As simple as useLLM().

Whisper Turbo is a fast, cross-platform Whisper implementation, designed to run entirely client-side in your browser/electron app.

luma.gl is a GPU toolkit for the Web-focused primarily on data visualization use cases. luma.gl aims to provide support for GPU programmers that need to work directly with shaders and want a low abstraction API that remains conceptually close to the WebGPU and WebGL APIs. Unlike other common WebGL APIs, the developer can choose to use the parts of luma.gl that support their use case and leave the others behind. While generic enough to be used for general 3D rendering, luma.gl's mandate...

WebLLM is a modular, customizable javascript package that directly brings language model chats directly onto web browsers with hardware acceleration. Everything runs inside the browser with no server support and is accelerated with WebGPU. We can bring a lot of fun opportunities to build AI assistants for everyone and enable privacy while enjoying GPU acceleration. WebLLM offers a minimalist and modular interface to access the chatbot in the browser. The WebLLM package itself does not come...

Rio is a terminal application that’s built with Rust, WebGPU, Tokio runtime. It targets to have the best frame per second experience as long you want, but is also configurable to use as minimal from GPU. It also relies on Rust memory behavior, since Rust is a memory-safe language that employs The terminal renderer is based on redux state machine, lines that has not updated will not suffer a redraw. Looking for the minimal rendering process in most of the time. Rio is also designed...