Stars
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
A reading path for CPU performance engineering, from one instruction to production inference. Primary sources only, with a runnable benchmark for every section.
PyTorch code and models for the DINOv2 self-supervised learning method.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
100 days of LLM inference engineering — daily posts, experiments, and visualizations
A complete computer science study plan to become a software engineer.
A straightforward method for training your LLM, from downloading data to generating text.
Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, be…
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
Learn AI Engineering! Learn it. Build it. Ship it for others.
Introduction to PyTorch, covering tensor initialization, operations, indexing, and reshaping.
A SQL database in Rust: SQLite-compatible, now also speaking Postgres (experimental). The LLVM of databases.
The Dark Arts of Advanced and Unsafe Rust Programming
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
The agent that grows with you
Advanced Machine Learning Specialization on Coursera
The batteries-included agent harness.
A high-performance, ultra low-latency trading terminal and AI-infused daemon built completely in Rust.
Code, labs, and resources for O'Reilly AI Systems Performance Engineering: GPU optimization, distributed training, inference scaling, and full-stack tuning.
A curated resource list for learning AI performance engineering, from GPU fundamentals to production inference.
Implementation of J.R. Quinlan's ID3 decision tree algorithm from his seminal 1986 paper 'Induction of Decision Trees'
Minimalistic 4D-parallelism distributed training framework for education purpose
Release repo for our SLAM Handbook
A course on aligning smol models.
High-performance framework for building interactive workflow systems in Rust. Designed for complex workflows and multi-agent systems