Repository Index

Open standard for machine learning interoperability

• deep-learning
• deep-neural-networks
• neural-network
• onnx

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

• cntk
• visualization
• tensorflow
• model-converter

An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models

• kubernetes
• machine-learning
• deployment
• serving

Open-source library of optimized deep learning operations (matmul, convolution, attention) for CPUs (x64, AArch64, RISC-V) and Intel GPUs. Used by PyTorch, TensorFlow, OpenVINO, and ONNX Runtime.

• onednn
• oneapi
• performance
• cpp

How to Copy Text from Images ? Answer is TextSnatcher !. Perform OCR operations in seconds on Linux Desktop.

• gtk3
• ocr
• linux-app
• tesseract-ocr

Gp.nvim (GPT prompt) Neovim AI plugin: ChatGPT sessions & Instructable text/code operations & Speech to text [OpenAI, Ollama, Anthropic, ..]

• copilot
• neovim
• nvim
• speech-to-text

Vulkan, OptiX and CUDA Interoperation Modular Rendering Library and Framework for PC/Linux/Android

• vulkan
• raytracing
• graphics-engine
• graphics-library

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.

• ai
• gguf
• gpu
• inference

This repository provides a set of tools and libraries to integrate Intel® OpenVINO™ Toolkit with ROS 2 (Robot Operating System), enabling efficient deployment of deep learning models for computer vision applications on Intel® hardware.

Accelerated tensor operations and dynamic neural networks based on reverse mode automatic differentiation for every device that can run Swift - from watchOS to Linux

• deep-learning
• deep-neural-networks
• gradient-descent
• automatic-differentiation

Conflict-free merge for DataFrames, JSON, ML models & distributed agents — powered by CRDTs. The first merge library where every operation is mathematically guaranteed to converge.

• collaborative-editing
• conflict-resolution
• crdt
• data-engineering