There are early discussions of implementing WebGPU support in llama.cpp/ggml. Look into contributing and bringing the support in llm.js.

• Webgpu backend ggml-org/ggml#585
• ggml : add WebGPU backend ggml-org/llama.cpp#7773

Some projects/resources related to WebGPU:

• https://eliemichel.github.io/LearnWebGPU/ (Great place to start learning)
• https://github.com/mlc-ai/web-llm
• https://github.com/mlc-ai/web-stable-diffusion