Lists (17)
Stars
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Python code for classification of documents into different classes using machine learning
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Open-source MITM proxy to intercept, inspect, and mock network traffic.
EasyMDE: A simple, beautiful, and embeddable JavaScript Markdown editor. Delightful editing for beginners and experts alike. Features built-in autosaving and spell checking.
The all-in-one, open-source backend platform for agentic coding. InsForge gives your coding agent database, auth, storage, compute, hosting, and AI gateway to ship full-stack apps end-to-end.
A minimal GPU design in Verilog to learn how GPUs work from the ground up
On-device AI across mobile, embedded and edge for PyTorch
Running any GGUF SLMs/LLMs locally, on-device in Android
GPEmu, a GPU emulator for faster and cheaper prototyping and evaluation of deep learning system research
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
Foundation model for tiny devices; 14mb, 26m params, 1-6k toks/sec on mobiles, wearables smart home and robots.
Tom Select is a lightweight (~16kb gzipped) hybrid of a textbox and select box. Forked from selectize.js to provide a framework agnostic autocomplete widget with native-feeling keyboard navigation.…
Mathematical animations for the web — Manim in TypeScript
🤘 TT-NN operator library, and TT-Metalium low level kernel programming model.
CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds
From the Transistor to the Web Browser, a rough outline for a 12 week course
The 2013 edition of the Source SDK
Standards compliant, fast, secure markdown processing library in C
Build script for BareMetal OS and its related utilities