wllama V3 ships WebGPU, multimodal and tool calling for in-browser llama.cpp inference
ngxson · x · 2026-09-19
wllama, ngxson's WebAssembly binding for llama.cpp (1.2k GitHub stars), just released V3 with three headline features: WebGPU support, multimodal input (image and audio), and tool calling. It exposes a fully-typed OpenAI-compatible API, and the author built the openjev demo on top of it.
Weights load from Hugging Face and cache in the browser with inputs never leaving the page, making it a solid base for backend-free local AI web apps.
Related event: wllama V3 and openjev bring local LLMs to the browser(3 posts)→
More from Infra
- Orbital AI datacenters break even near $200/kg launch cost, versus ~$3,000 today — shashib · 2026-11-04
- Why NVIDIA profits by refusing to vertically integrate its full stack — AccBalanced · 2026-11-04
- eggshell released: a bare-metal Go unikernel that runs unmodified Linux binaries — evilsocket · 2026-11-04
- GitHub incident degrades Pull Requests, Git operations, Issues and Actions — aniketmaurya · 2026-11-04
- Nvidia struggles to hire RL talent from Anthropic, highlighting chipmakers' reinforcement learning gap — teortaxesTex · 2026-11-04
- Sam Altman? No—Bezos Calls for Nuclear-Powered Offshore Data Center Platforms — beffjezos · 2026-11-04