The goal of RamaLama is to make working with AI boring.

Website for monitoring and instant alerts on Nvidia Shop's Founders Edition GPU availability.

an adaptable text editor

A new markup-based typesetting system that is powerful and easy to learn.

LLM101n: Let's build a Storyteller

Minimal Mamba-2 implementation in PyTorch

A complement to pgvector for high performance, cost efficient vector search on large workloads.

LSP-AI is an open-source language server that serves as a backend for AI-powered functionality, designed to assist and empower software engineers, not replace them.

helix gpui frontend

Solve puzzles. Improve your pytorch.

DSPy: The framework for programming—not prompting—language models

The official Meta Llama 3 GitHub site

LLM inference in C/C++

PtrHash minimal perfect hash function, based of PTHash

Python bindings to PDFium

1️⃣🐝🏎️ The One Billion Row Challenge -- A fun exploration of how quickly 1B rows from a text file can be aggregated with Java

Simple, safe way to store and distribute tensors

Coz: Causal Profiling

🕳 bore is a simple CLI tool for making tunnels to localhost

a structural diff that understands syntax 🟥🟩

AICI: Prompts as (Wasm) Programs

a verbose example on using metal with C++ to perform arbitrary compute on GPUs

CUDA on non-NVIDIA GPUs

A simple and efficient Mamba implementation in pure PyTorch and MLX.

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

MLX: An array framework for Apple silicon

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

🎧 Open source Spotify client that doesn't require Premium nor uses Electron! Available for both desktop & mobile!