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

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

LLM inference in C/C++

Build robust LLM applications with true composability 🔗

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

ECE 459: Programming for Performance

Models and examples built with TensorFlow

Print-friendly, minimalist CV page

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

GPT4 powered terminal assistant

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

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

You like pytorch? You like micrograd? You love tinygrad! ❤️

openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system in 275+ supported cars.

An Open-Ended Embodied Agent with Large Language Models

A browser extension that enhance search engines with ChatGPT

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Accurate answers and instant citations for your documents.

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Collection of Summer 2025 tech internships!

Python data Manipulation, visualizations and Natural Language Processing analysis for Wall Street Journal web scraping project #2 for NYC Data Science Academy bootcamp

🍎 Screensaver inspired by Apple's Event on October 30, 2018

Implement Transformers (and Deep Learning) from scratch in NumPy

Robust Speech Recognition via Large-Scale Weak Supervision

Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.

Generate a cute welcome message for yourself each day

Official Algorithm Implementation of ICML'23 Paper "VIMA: General Robot Manipulation with Multimodal Prompts"

A sandbox repo for grounded question answering with Cohere and Google Search

A demonstration of how a toy (but usable!) semantic search engine can be quickly built using Cohere's platform.