Andrew Chan

yalm. Yet Another Language Model: LLM inference in C++/CUDA, no libraries except for I/O

deepseek.cpp. CPU inference for the DeepSeek family of large language models in C++

fire-simulation. :fire: Real-time fire simulation on the GPU!

andrewkchan.github.io. Source code for my personal site

lit-splat. Experimental Relightable Gaussian Splat viewer

pytorch_mesh_renderer. Some implementations of differentiable 3D mesh renderers using PyTorch with examples

puffscript. Statically typed, imperative programming language that compiles to WebAssembly

very-tiny-diffusion. Jupyter Notebook

crawler-transcripts.

SoundFoundry. :musical_note: A fully featured music player built in React and Redux. Modeled after SoundCloud and uses their API.

wave-function-collapse. Annotated implementation of wave function collapse algorithm

JavaScript-Guide. A mirror of my guide from GitBooks

farmr. Farmr is your personal agronomist, democratizing agricultural knowledge for farmers everywhere.

search-engine-day-1. :mag_right: Dynamic indexer supporting incremental indexing of text documents. Implements a basic vector model and provides free and phrase text search queries.

radio-map. Geolocational internet radio that plays the nearest (user-placed) radio station.

deforum-stable-diffusion-mps. Adding support for (https://github.com/deforum-art/deforum-stable-diffusion) on Apple M1 Macs

scaling-book. Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs

slacker. React tutorial - slack clone

pbf-bench. Visual understanding and comic explanation benchmark for LLMs

OpenSplat. Production-grade 3D gaussian splatting with CPU/GPU support for Windows, Mac and Linux 🚀

tweet-runner. Game in which enemy spawns are affected by Twitter in realtime.