Search awesome repositories

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

Compresses linked and inline javascript or CSS into a single cached file.

python parser for human readable dates

Sane and flexible OpenAPI 3 schema generation for Django REST framework.

POT : Python Optimal Transport

A Python tool to visualize + enforce dependencies, using modular architecture 🌎 Open source 🐍 Installable via pip 🔧 Able to be adopted incrementally - ⚡ Implemented with no runtime impact ♾️ Interoperable with your existing systems 🦀 Written in rust

LLM speculative inference server for heterogeneous hardware & consumer GPUs

Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

Feature rich robust FastAPI template.

Sequential model-based optimization with a `scipy.optimize` interface

Build, Store, and Distribute your Applications and Containers

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

Adaptive Experimentation Platform

Minimalistic large language model 3D-parallelism training

LLMRouter: An Open-Source Library for LLM Routing

The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.

OpenStack Storage (Swift). Mirror of code maintained at opendev.org.

Community maintained hardware plugin for vLLM on Ascend

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台，我们欢迎开源爱好者发起任何有意义的pr！

Concatenate a directory full of files into a single prompt for use with LLMs

Extensible memoizing collections and decorators

Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Cobbler is a versatile Linux deployment server

A static website and blog generator

Send email in Python conveniently for gmail using yagmail

Make awesome display tables using Python

Official inference repo for FLUX.2 models

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

Asynchronous Python ODM for MongoDB