Issue 2026-09-30 · Industry · 开源 · 研究
Hugging Face open-sources fastest WebGPU kernels for local AI
Hugging Face open-sourced WebGPU kernels for over 200 common ML operations that run entirely locally in browsers. The optimizations are being upstreamed to Transformers.js, ONNX Runtime Web, LiteRT.js, and more.
Read original ↗- Ternary Bonsai 2 models released, 2B version runs locally in browser
- Talus: 23M-parameter diffusion model for game terrain runs in browser
- Developer rebuilds Mozilla's Orbit with local inference
- Opinion: AI Has Crossed a Line and Should Be Regulated Like Banks
- Open-source inside-llm visualizes LLM internals and quantization gaps