WebGPU
WebGPU is a web standard graphics and compute API developed by the W3C that provides browsers with direct access to underlying GPU hardware. As the successor to WebGL, it supports modern graphics pipeline operations and general-purpose GPU computing (GPGPU), enabling high-performance 3D rendering, image processing, and machine learning inference. WebGPU is designed to align with native graphics APIs such as Vulkan, Metal, and Direct3D 12, offering lower CPU overhead and finer-grained GPU control.
Core Facts
WebGPU is a W3C-standardized browser graphics and compute API that was officially released in Chrome in 2023, designed to replace WebGL.
WebGPU introduces compute shaders, multi-threaded rendering, and more fine-grained GPU resource management mechanisms, where compute shaders can offload intensive tasks to the GPU.
WebLLM is a high-performance in-browser LLM inference engine that aims to move the entire model inference pipeline to the client-side browser for execution, with no server support required.
Timeline (last 90 days)
Implementing real-time camera interaction in the browser typically requires combining WebGL or WebGPU for real-time rendering, using WebAssembly to run computer vision models (such as MediaPipe and TensorFlow.js), and handling low-latency transmission through WebRTC.
WebGPU supports compute shaders, multi-threaded command submission and lower driver overhead, and can also handle general-purpose computing tasks in addition to graphics drawing.
Pascal Editor is an open-source web-based editor written in TypeScript, with underlying rendering relying on React Three Fiber (R3F) and WebGPU.
WebGPU is a modern graphics and compute API exposed by the browser, allowing JavaScript to call the GPU directly for parallel matrix operations; WASM is a binary instruction format that can run in the browser, mainly on the CPU, with broader compatibility but slower speed.
The browser-side RAG process consists of four steps: retrieval, gating, prompt construction, and generation; for generation it prefers WebGPU, and falls back to WASM running on the CPU if unsupported.
WebGPU is a new-generation browser graphics standard that is being rolled out, closer to the low-level models of Vulkan/Metal/DirectX 12, and can provide lower CPU overhead and stronger parallel computing capability.
For applications rendering tens of thousands of small objects, WebGPU's instanced rendering and compute shaders can significantly reduce the number of draw calls per frame.
When the browser does not support WebGPU, Decide Live automatically falls back to running on WASM (CPU).
Decide Live executes on WebGPU via transformers.js, generates zero tokens, and uploads no data.
Go Outside runs models via WebLLM (@mlc-ai/[email protected]), an inference engine open-sourced by MLC that can compile models to WebGPU.
40 more timeline events
All Facts (20)
WebGPU is a W3C-standardized browser graphics and compute API that was officially released in Chrome in 2023, designed to replace WebGL.
80%VerifiedWebGPU introduces compute shaders, multi-threaded rendering, and more fine-grained GPU resource management mechanisms, where compute shaders can offload intensive tasks to the GPU.
80%VerifiedWebLLM is a high-performance in-browser LLM inference engine that aims to move the entire model inference pipeline to the client-side browser for execution, with no server support required.
75%VerifiedONNX Runtime Web compiles the ONNX runtime to WebAssembly to enable cross-platform model inference; ONNX was jointly introduced by Microsoft and Facebook.
75%VerifiedCompared to WebGL, which is based on OpenGL ES, WebGPU introduces compute shaders, a more fine-grained resource binding model, and pipeline state management, allowing general-purpose parallel computing tasks (GPGPU) to be executed on the GPU.
65%VerifiedWebGPU, as the next-generation successor to WebGL, officially landed in Chrome in 2023, delivering performance closer to that of native graphics APIs.
65%VerifiedWebGPU是W3C正在推进的新一代Web图形与计算API标准，旨在替代WebGL，对标Vulkan、Metal、Direct3D 12
65%UnverifiedWebContainer目前主要支持Node.js生态，对编译型语言（如Rust、Go、C++）或系统级调用的场景仍需传统后端容器方案
90%UnverifiedSwiftShader is a high-performance CPU renderer developed by Google, supporting Vulkan and WebGPU.
70%UnverifiedWGSL (WebGPU Shading Language) is the official shading language of WebGPU.
70%UnverifiedChrome officially enabled WebGPU support in 2023.
70%UnverifiedWebGPU introduces compute shader capabilities comparable to Vulkan/Metal/D3D12, enabling general-purpose GPU computing (GPGPU).
60%UnverifiedThe browser-side AI capability technology stack is jointly composed of underlying hardware acceleration standards such as WebGPU and WebNN.
60%UnverifiedImplementing real-time camera interaction in the browser typically requires combining WebGL or WebGPU for real-time rendering, using WebAssembly to run computer vision models (such as MediaPipe and TensorFlow.js), and handling low-latency transmission through WebRTC.
50%UnverifiedPascal Editor is an open-source web-based editor written in TypeScript, with underlying rendering relying on React Three Fiber (R3F) and WebGPU.
50%UnverifiedWebGPU supports compute shaders, multi-threaded command submission and lower driver overhead, and can also handle general-purpose computing tasks in addition to graphics drawing.
50%UnverifiedThe browser-side RAG process consists of four steps: retrieval, gating, prompt construction, and generation; for generation it prefers WebGPU, and falls back to WASM running on the CPU if unsupported.
50%UnverifiedWebGPU is a modern graphics and compute API exposed by the browser, allowing JavaScript to call the GPU directly for parallel matrix operations; WASM is a binary instruction format that can run in the browser, mainly on the CPU, with broader compatibility but slower speed.
50%UnverifiedWebGPU is a new-generation browser graphics standard that is being rolled out, closer to the low-level models of Vulkan/Metal/DirectX 12, and can provide lower CPU overhead and stronger parallel computing capability.
50%UnverifiedFor applications rendering tens of thousands of small objects, WebGPU's instanced rendering and compute shaders can significantly reduce the number of draw calls per frame.
50%