Awesome GitHub RepositoriesComputational Graph Visualizers

Llama.cpp is an inference engine designed for the local execution of text-based and multimodal language models on consumer hardware. It provides a core environment for running models that process both text and image inputs, utilizing hardware-accelerated backends to optimize performance across diverse CPU and GPU architectures. The project distinguishes itself by offering a lightweight HTTP server that adheres to standard API specifications, enabling chat completion, embeddings, and reranking services. It includes a suite of tools for model quantization and conversion, which reduces memory us

This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation. The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex

This project is a machine learning array framework and tensor computation library designed for high-performance numerical computing. It provides a comprehensive suite of tools for constructing and training neural networks, featuring an automatic differentiation engine that facilitates gradient-based optimization and complex mathematical modeling. The library distinguishes itself through a unified memory architecture that allows data to be shared across CPU and GPU devices without explicit copies, significantly reducing data movement overhead. Its execution model relies on a lazy evaluation en

This project is a deep learning framework designed for constructing, training, and deploying neural networks across diverse hardware environments. It functions as a high-performance tensor computation library that provides both imperative and symbolic programming interfaces, allowing developers to balance flexible, step-by-step model building with the efficiency of compiled computation graphs. The framework distinguishes itself through a hybrid execution engine that integrates declarative graph compilation with imperative runtime logic. It supports scalable, distributed training across multip

ONNX is an open-source standard for machine learning interoperability that provides a unified format for representing neural network models. By defining a common set of operators and a standardized file structure, it enables models to be shared, exported, and executed consistently across different training frameworks and software ecosystems. The project functions as an intermediate representation layer that decouples model development from deployment. It utilizes a language-neutral binary serialization format to store model structures and weights, ensuring that computational graphs remain por

OpenVINO is an AI inference engine and model serving platform designed to execute optimized deep learning models across CPUs, GPUs, and NPUs through a unified API. It includes a model optimization toolkit for converting, quantizing, and compressing models from various frameworks, alongside a specialized generative AI runtime for large language models. The project distinguishes itself through a plugin-based hardware acceleration layer that maps neural network operations to vendor-specific drivers. It features advanced execution mechanisms such as continuous batching, speculative decoding, and

TensorBoard is a visualization toolkit for tracking and analyzing machine learning model training progress and performance using TensorFlow event logs. It provides a monitoring dashboard for plotting scalar metrics, tensor distributions, and training curves, and includes specialized tools for visualizing neural network computational graphs and projecting high-dimensional embeddings. The project enables side-by-side comparison of multiple training runs to analyze the impact of hyperparameters on model outcomes. It also features a high-dimensional embedding projector and a graph visualizer for

MMdnn 是一个深度学习模型转换与迁移工具，旨在实现 TensorFlow、PyTorch 和 Keras 等不同框架之间的神经网络架构与权重转换。它利用标准化的中间表示（IR）将网络结构和权重与特定框架的实现解耦，从而支持在不同环境中转换预训练模型。 该项目的特色在于能从中间表示生成原生的 Python 重构代码，允许在目标环境中重建和微调模型。它还包含用于移动端模型部署的专用工具，可将深度学习模型转换为 CoreML 和 TensorFlow Lite 等移动兼容格式。 该系统提供了一套更广泛的功能，包括用于检查图结构和元数据的神经网络架构可视化，以及用于验证转换后模型是否保持原始行为和精度的模型推理执行。其他实用程序还可处理从远程仓库获取预训练权重以及组装可部署的模型检查点。