🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

A new bootable USB solution.

Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS ev…

Python frame stack sampler for CPython

Python tool for converting files and office documents to Markdown.

A simple screen parsing tool towards pure vision based GUI agent

深度学习经典、新论文逐段精读

🤖 Just a command runner

Certbot is EFF's tool to obtain certs from Let's Encrypt and (optionally) auto-enable HTTPS on your server. It can also act as a client for any other CA that uses the ACME protocol.

[NeurIPS'24 Spotlight, ICLR'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an …

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

TorchServe images with specific Python version working out-of-the-box.

Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.

Make websites accessible for AI agents

🙌 OpenHands: Code Less, Make More

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous …

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

A Lightweight Recommendation System

An extremely fast Python package and project manager, written in Rust.

Serve, optimize and scale PyTorch models in production

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.

Standardized Serverless ML Inference Platform on Kubernetes

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

Large Language Model Text Generation Inference

A blazing fast inference solution for text embeddings models

Python actor framework for heterogeneous computing.

Finally, a JSONPath implementation for Python that aims to be standard compliant. That's all. Enjoy!

A feature-rich command-line audio/video downloader

A modular graph-based Retrieval-Augmented Generation (RAG) system