WebLLM runs an AI in your browser, talks to your GPU

This project brings language model chats directly onto web browsers. Everything runs inside the browser with no server support and accelerated with WebGPU. We can bring a lot of fun opportunities to build AI assistants for everyone and enable privacy while enjoying GPU acceleration.


These models are usually big and compute-heavy. To build a chat service, we will need a large cluster to run an inference server, while clients send requests to servers and retrieve the inference output. We also usually have to run on a specific type of GPUs where popular deep-learning frameworks are readily available.

This project is our step to bring more diversity to the ecosystem. Specifically, can we simply bake LLMs directly into the client side and directly run them inside a browser? If that can be realized, we could offer support for client personal AI models with the benefit of cost reduction, enhancement for personalization, and privacy protection. The client side is getting pretty powerful.

Won’t it be even more amazing if we can simply open up a browser and directly bring AI natively to your browser tab? There is some level of readiness in the ecosystem. WebGPU has just shipped and enables native GPU executions on the browser.

Still, there are big hurdles to cross, to name a few:

  • We need to bring the models somewhere without the relevant GPU-accelerated Python frameworks.
  • Most of the AI frameworks rely heavily on optimized computed libraries that are maintained by hardware vendors. We need to start from scratch.
  • Careful planning of memory usage, and aggressive compression of weights so that we can fit the models into memory.

We also do not want to only do it for just one model. Instead, we would like to present a repeatable and hackable workflow that enables anyone to easily develop and optimize these models in a productive Python-first approach, and deploy them universally, including on the web.

Besides supporting WebGPU, this project also provides the harness for other kinds of GPU backends that TVM supports (such as CUDA, OpenCL, and Vulkan) and really enables accessible deployment of LLM models.

Source: WebLLM github

Organisational Structures | Technology and Science | Military, IT and Lifestyle consultancy | Social, Broadcast & Cross Media | Flying aircraft