jovsa

othello_mamba

Evaluating the Mamba architecture on the Othello game

megablocks-public

AlphaCodium

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

pmpp__programming_massively_parallel_processors

Examples and exercises from the book Programming Massively Parallel Processors - A Hands-on Approach. David B. Kirk and Wen-mei W. Hwu (Third Edition)

lectures

Material for gpu-mode lectures

Vesuvius-Grandprize-Winner

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

StackRabbit

An AI for playing NES Tetris at a high level. Based primarily on search & heuristic, with high quality board evaluation through value iteration.

megablocks

vllm

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

monaco

Quantify uncertainty and sensitivities in your computer models with an industry-grade Monte Carlo library.

petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

powerlaw

aleatory

📦 Python library for Stochastic Processes Simulation and Visualisation

ai_and_memory_wall

AI and Memory Wall

RASP

An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"

numpy-ml

Machine learning, in numpy

Autodiff-Puzzles

codebase

Official code repo for the MARL book (www.marl-book.com)

boardlaw

Scaling scaling laws with board games.

openfold

Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2

chatarena

ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

llama.cpp

LLM inference in C/C++

AutoDMP

ColossalAI

Making large AI models cheaper, faster and more accessible

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

langchain

🦜🔗 Build context-aware reasoning applications

communitynotes

Documentation and source code powering Twitter's Community Notes

tangent

Source-to-Source Debuggable Derivatives in Pure Python