A vector index built on TurboQuant, written in Rust with Python bindings

PostgreSQL with built-in versioned layer storage and Time Travel. See your database as it existed at any point in time.

The financial transactions database designed for mission critical safety and performance.

TiDB is built for agentic workloads that grow unpredictably, with ACID guarantees and native support for transactions, analytics, and vector search. No data silos. No noisy neighbors. No infrastruc…

Blazing fast, structured, leveled logging in Go.

Resumes generated using the GitHub informations

Go package for computer vision using OpenCV 4 and beyond. Includes support for DNN, CUDA, OpenCV Contrib, and OpenVINO.

Train high-quality text-to-image diffusion models in a data & compute efficient manner

Container images and tool for running machine learning with Rust on Amazon SageMaker

Inference at the speed of light.

A JAX research toolkit for building, editing, and visualizing neural networks.

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

A curriculum for learning about foundation models, from scratch to the frontier

LLM training in simple, raw C/CUDA

GO Simple Tunnel - a simple tunnel written in golang

[ECCV 2024] Official PyTorch implementation of "Getting it Right: Improving Spatial Consistency in Text-to-Image Models"

An AWS Lambda powered HTTP/SOCKS web proxy

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progres…

A comprehensive Python package template to kickstart and standardize your MLOps initiatives and data pipelines.

Devika is the first open-source implementation of an Agentic Software Engineer. Initially started as an open-source alternative to Devin.

Simple Adaptation of BitNet

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

lightweight, standalone C++ inference engine for Google's Gemma models.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Unveiling the Knowledge of Hindu Scriptures

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

Selenium WebDriver client for Rust, for automated testing of websites

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.