Direct File

Architectural Metapatterns book and wiki

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

🙌 OpenHands: Code Less, Make More

Literature references for “Designing Data-Intensive Applications”

A curated list of software and architecture related design patterns.

Learn Low Level Design (LLD) and prepare for interviews using free resources.

Curated Data Science resources (Free & Paid) to help aspiring and experienced data scientists learn, grow, and advance their careers.

A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

AWS CDK Builder is a browser-based tool designed to streamline bootstrapping of Infrastructure as Code (IaC) projects using the AWS Cloud Development Kit (CDK).

SQL tips and tricks

SGLang is a fast serving framework for large language models and vision language models.

An Engine-Agnostic Deep Learning Framework in Java

Demo applications showcasing DJL

A universal scalable machine learning model deployment solution

Open-source Android/Desktop remake of Civ V

Multiplayer top-down shooter made from scratch in C++. Play in your Browser! https://hypersomnia.io Made in 🇵🇱

Procedural tree generator written with JavaScript and Three.js

A library for training and deploying machine learning models on Amazon SageMaker

Tools to Design or Visualize Architecture of Neural Network

A high-throughput and memory-efficient inference and serving engine for LLMs

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

Efficent platform for inference and serving local LLMs including an OpenAI compatible API server.

This is an online course where you can learn and master the skill of low-level performance analysis and tuning.

Easy, fast and very cheap training and inference on AWS Trainium and Inferentia chips.

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Official NetHack Git Repository

[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding