rawsh

autogen

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

vllm

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

biome

A toolchain for web projects, aimed to provide functionalities to maintain them. Biome offers formatter and linter, usable via CLI and LSP.

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

cog

Containers for machine learning

sweep

Sweep: open-source AI-powered Software Developer for small features and bug fixes.

outlines

Structured Text Generation

pr-agent

🚀CodiumAI PR-Agent: An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More! 💻🔍

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

CTranslate2

Fast inference engine for Transformer models

exllama

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

OpenPipe

Turn expensive prompts into cheap fine-tuned models

llama2.mojo

Inference Llama 2 in one file of pure 🔥

aurae

Distributed systems runtime daemon written in Rust.

autodistill

Images to inference with no labeling (use foundation models to train supervised models).

AppleJuice

Apple BLE proximity pairing message spoofing

barco

Linux containers from scratch in C.

LookaheadDecoding

loom

Multiversal tree writing interface for human-AI collaboration

Fooocus-MRE

Focus on prompting and generating

textbook_quality

Generate textbook-quality synthetic LLM pretraining data

ALCE

[EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627

pinecone-vercel-starter

Pinecone + Vercel AI SDK Starter

code-indexer-loop

Code Indexer Loop is a Python library for indexing and retrieving source code files through an integrated vector database that's continuously and efficiently updated.

speculative-decoding

Explorations into some recent techniques surrounding speculative decoding

easyreadme

Easyreadme helps you simplify README creation and generate visually stunning ones with the help of AI and elegant pre-designed templates.

branches

Prototype advanced LLM algorithms for reasoning and planning.

queues-demo

A demo of Cloudflare Queues

verbomate

Run LLM generated scripts in CLI