siddrrsh

vllm

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

ambientGPT

gemma-2B-10M

Gemma 2B with 10M context length using Infini-attention.

ArchiveBox

🗃 Open source self-hosted web archiving. Takes URLs/browser history/bookmarks/Pocket/Pinboard/etc., saves HTML, JS, PDFs, media, and more...

petals

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

readings

This is a list of readings for CS348K.

asitop

Perf monitoring CLI tool for Apple Silicon

mlx

MLX: An array framework for Apple silicon

mlxcli

Run large models from the terminal using Apple MLX.

PicoMLXServer

The easiest way to run the fastest MLX-based LLMs locally

mlxserver

Start a server from the MLX library.

Awesome-LLMs-Evaluation-Papers

The papers are organized according to our survey: Evaluating Large Language Models: A Comprehensive Survey.

funsearch

megablocks

cog

Containers for machine learning

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

personal

The source for my personal static website

putting-the-you-in-cpu

A technical explainer by @kognise of how your computer runs programs, from start to finish.

ggml

Tensor library for machine learning

llama.cpp

LLM inference in C/C++

multiagent-particle-envs

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

ChatGPT

Reverse engineered ChatGPT API

learn-react-app

Application that will help you learn React fundamentals. Install this application locally - there's tutorial, code snippets and exercises. The main objective of this project is to help you get off the ground with React!

openai-gpt3

GPT3 website using Reactjs

mistral

Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.

Cerbo

Perform Efficient ML/DL Modelling easily

python-coinmarketcap

CoinMarketCap Python API Wrapper

Stanford-LaTeX-Poster-Template

Stanford LaTeX poster template

coding-interview-university

A complete computer science study plan to become a software engineer.