WebGPU
PulseAugur coverage of WebGPU — every cluster mentioning WebGPU across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
ProxyFace adds local, emotional avatars to AI chats
ProxyFace is an open-source project that adds a local, expressive avatar to AI interactions. It utilizes a small, on-device emotion model and eye-tracking to make the avatar react to AI output and the user's gaze. The p…
-
Researchers create high-fidelity mobile avatars using local blendshapes
Researchers have developed a new method for creating high-fidelity human avatars that can operate on mobile devices. This approach utilizes local linear blendshapes within specific body parts to capture complex appearan…
-
Run LLMs locally with LFM 2 and Transformers.js, using WebGPU
Thomas Bley has released new slides detailing how to run Large Language Models (LLMs) locally using LFM 2. The presentation also covers using Transformers.js with WebGPU for privacy filters, function calling, and embedd…
-
Born ML framework achieves pure Go GPU acceleration with v0.8.0 update
Born ML has released version 0.8.0, transitioning its GPU backend from Rust's wgpu-native to a pure Go implementation called gogpu/wgpu. This change eliminates the need for external runtime dependencies like .dll or .so…
-
Nvidia's Nemotron 3 Nano Omni and Llama.cpp enable local LLM execution
Thomas Bley has released new presentation slides detailing how to run large language models locally. The slides cover Nvidia's Nemotron 3 Nano Omni, built-in tools for Llama.cpp, and the use of Transformers.js with WebG…
-
Hugging Face guides local AI Chrome extensions with Transformers.js
Hugging Face has released a guide detailing how to create a Chrome extension that runs AI models locally within the browser. This approach, utilizing Transformers.js and Manifest V3, offers benefits like enhanced user p…
-
Local AI agent runs in Chrome using Gemma 4 and WebGPU
A new AI agent has been developed that runs locally within the Chrome browser, eliminating the need for a separate server. This agent leverages Google's Gemma 4 model and WebGPU technology for its operations. The develo…
-
Rust-based Demucs offers local, GPU-accelerated music stem separation
A new Rust implementation of the HTDemucs v4 music separation model, named Demucs CLI, has been released. This tool can split songs into individual stems like vocals, drums, and bass, running entirely locally on a user'…
-
BrowserAI enables local LLM execution with WebGPU acceleration
BrowserAI is an open-source project enabling large language models to run directly within a web browser using WebGPU for accelerated performance. This approach ensures 100% privacy as all processing occurs locally, elim…