Running LLMs in the Browser with WebGPU

Step-by-step guide to running inference for small language models directly in the browser using WebGPU acceleration.

@ducpham · Yesterday

15 min read41.2K

Ongoing

Practical machine learning for frontend and full-stack developers. No PhD required.

@ducpham

ML Engineer turned technical writer. Making machine learning accessible to web developers.

31.5K followers104 articles

A deep dive into the mental model shift RSC brings to React applications, and why it matters for the future of web development.

Practical patterns for scaling real-time WebSocket connections using connection pooling, sharding, and edge compute.

Building event-driven microservices using Apache Kafka, TypeScript, and modern streaming patterns.