Open-source alternatives to Apache Tvm

Candle is a minimalist machine learning framework and deep learning inference engine designed for the Rust programming language. It functions as a low-level tensor computation library, providing the necessary primitives for multi-dimensional array operations and mathematical transformations required to execute pre-trained neural network models. The framework distinguishes itself through a focus on memory efficiency and hardware utilization. It employs static-typed tensor operations to enforce shape validation and memory safety at compile time, while utilizing a lazy-loaded computational graph

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

Ivy is a machine learning framework transpiler and model converter designed to translate code and computational graphs between different deep learning ecosystems. It serves as a portability tool for migrating model architectures and logic across competing frameworks to enable flexible deployment. The system achieves cross-framework conversion by utilizing abstract syntax tree analysis to rewrite source code and by employing a computational graph tracer to capture tensor flows and operation sequences during live execution. This process allows for the translation of both high-level model defini

OneFlow is a deep learning framework and distributed execution engine designed for building, training, and deploying neural network architectures. It functions as a scalable neural network library that allows for the development of deep learning models and their execution across distributed hardware. The project includes a machine learning graph compiler used to optimize neural network execution graphs. This allows for the acceleration of model performance and the reduction of latency during both training and inference. The framework covers broad capability areas including large-scale model

Triton is a parallel computing framework and high-level programming language designed for writing custom compute kernels. It functions as a deep learning compiler, translating complex mathematical operations into high-throughput instructions that maximize hardware utilization and memory efficiency on graphics processing units. The framework distinguishes itself through a hardware-agnostic compute abstraction that allows developers to define kernels without manual low-level tuning. It employs just-in-time compilation to generate optimized binary instructions at runtime, utilizing static data f

MAME is a vintage hardware emulation platform designed to recreate the circuitry of arcade games, computers, and consoles to run original software on modern devices. It functions as a retro gaming preservation framework for managing, verifying, and archiving ROM sets and disk images to ensure long-term software accessibility. The project features a system debugging tool for inspecting emulated memory, CPU registers, and execution flow via breakpoints and disassembly. It also includes a Lua-based automation layer that exposes core system state and hardware controls for custom behavior and anal

Burn is a deep learning framework designed for building, training, and deploying neural networks using a modular architecture. As a machine learning library built in Rust, it provides a backend-agnostic computational engine that enables the execution of models across diverse hardware, including central processors, graphics processors, and web runtimes. The framework distinguishes itself through a highly portable design that allows developers to maintain a single workflow for both training and inference across heterogeneous environments. It incorporates advanced optimization techniques such as

This project is a deep learning library designed for training neural networks on irregular data structures, including graphs, 3D meshes, and point clouds. It functions as an extension to the PyTorch framework, providing specialized layers and kernels that enable the processing of complex, non-Euclidean information. The library distinguishes itself through a geometric deep learning toolkit that manages the unique requirements of graph-based data. It utilizes sparse matrix-based message passing to aggregate information across nodes and employs dynamic computational graph construction to accommo

MLC LLM is a machine learning compiler and inference engine designed to execute large language models locally across diverse hardware platforms, including desktop, mobile, and web environments. By utilizing machine learning compilation, the project transforms high-level model definitions into specialized, hardware-specific binary libraries. This process optimizes model weights and generates compute kernels tailored to the unique memory and processing characteristics of target graphics and mobile hardware. The engine distinguishes itself by providing a unified runtime abstraction that enables

Cog is a machine learning packaging tool and containerized model wrapper that bundles models and their dependencies into standardized Docker containers. It functions as an environment manager and inference server, ensuring consistent model execution across different hardware systems by resolving GPU drivers, system libraries, and Python dependencies. The project distinguishes itself by automatically generating RESTful HTTP servers and OpenAPI schemas based on defined model input and output types. It manages large model weights as external fixtures to optimize image size and utilizes a slot-ba

PlaidML is a deep learning compiler framework and cross-platform runtime designed to execute machine learning models on a wide variety of hardware targets. It functions as a hardware agnostic tensor engine that translates tensor models into executable code, allowing deep learning networks to run across different compute devices without requiring specific driver dependencies. The system enables the execution of models on custom or limited hardware by using JSON specifications to define device hardware. It employs a domain-specific language to describe tensor computations and provides a middle

Leaf is a machine learning framework and neural network architecture toolkit used for building, training, and deploying models. It functions as a hardware abstraction layer, mapping high-level computational graphs to low-level instructions across various CPU and GPU backends and operating systems. The system enables the design of flexible model structures through a modular architecture where reusable container layers encapsulate weights and mathematical operations. This allows for the composition of complex neural networks via nested components. The framework includes a data engineering pipe

Ivy is a machine learning framework transpiler and model converter designed to ensure deep learning portability. It serves as a tool for migrating source code and models between different deep learning frameworks while maintaining original functionality. The system enables cross-framework model portability by translating model weights, architectures, and source code. It uses abstract syntax tree based transpilation and computational graph tracing to capture execution flows and rewrite high-level logic into target framework code. The project covers model interoperability through weight-layout

Llamafile is a machine learning model runner and packager that enables local inference by bundling model weights and runtime environments into a single, self-contained executable. It functions as a cross-platform engine, allowing users to execute large language models and perform speech-to-text tasks directly on their own hardware without requiring external software dependencies or complex installations. The project distinguishes itself by utilizing a specialized binary format that allows the same executable to run natively across multiple operating systems and hardware architectures. It auto

SmolLM is a project dedicated to the development of small language models. It focuses on training and fine-tuning compact models that maintain high performance while utilizing fewer parameters. The project emphasizes efficient AI inference and on-device text generation, aiming to enable the deployment of lightweight models on edge devices with limited memory and processing power. It utilizes synthetic data generation to produce artificial datasets that improve the reasoning and training of these AI systems. The system supports a variety of optimization and training capabilities, including we

jetson-inference is a set of libraries and tools for executing optimized deep learning models on embedded GPU hardware. Its primary purpose is to enable real-time computer vision and AI inference at the edge with low latency and high throughput. The project distinguishes itself through high-performance streaming analytics and the ability to execute concurrent AI pipelines on auto-grade silicon. It provides specialized support for multi-sensor stream processing, utilizing zero-copy data transport to load camera frames directly into GPU memory. The codebase covers a broad surface of capabiliti

MiniCPM-V is a multimodal large language model and vision-language system designed for complex visual and linguistic understanding. It functions as an on-device AI model, providing the capacity to process text, images, and video as a compact neural network. The project is specifically developed as an edge AI framework, utilizing quantization and weight sharding to run on memory-constrained mobile chipsets. This allows for the deployment of multimodal intelligence directly on mobile operating systems for local inference. Its capabilities cover multimodal content analysis of high-resolution im

LiteRT-LM is a high-performance inference framework designed to execute large language models locally on mobile, desktop, and IoT hardware. It serves as an on-device model runtime that utilizes CPU, GPU, and NPU acceleration to provide low-latency processing. The framework is distinguished by its ability to process text, vision, and audio inputs through a single multi-modal inference engine. It features a local HTTP server that emulates OpenAI-compatible API endpoints and a WebGPU-based runtime for executing models directly within a web browser. To ensure output reliability, it includes a con

lite.ai.toolkit is a C++ computer vision toolkit designed for edge AI deployment. It enables the execution of pre-trained models for object detection, image classification, and segmentation on resource-constrained devices. The project features a multi-backend inference engine that supports the ONNX model runtime, allowing AI models to run across different hardware targets. It includes a GPU-accelerated pipeline specifically for NVIDIA hardware to reduce latency and increase processing speed. The toolkit covers a broad range of facial analysis capabilities, including emotion detection, gender

Super-Gradients is a PyTorch computer vision framework and training library designed for the full lifecycle of vision models. It functions as a deep learning model optimizer and a deployment toolkit for training and fine-tuning models across image classification, object detection, semantic segmentation, and pose estimation tasks. The project provides specific tools for model optimization, including teacher-student knowledge distillation and numerical precision compression to reduce memory and computational requirements. It also includes the implementation of the Yolo-NAS architecture for high

This project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene

Apex is a high-performance toolkit for PyTorch designed to coordinate distributed training, execute fused GPU kernels, manage mixed precision, and implement optimized distributed optimizers. It provides specialized tools for scaling model training across multiple GPUs and nodes to increase processing speed and throughput. The library features high-performance implementations of Adam and LAMB optimizers to reduce synchronization overhead and memory bottlenecks. It utilizes fused CUDA kernels to combine neural network operations, reducing memory overhead and increasing execution speed. The too

torch2trt is a tool for transforming PyTorch model modules into optimized TensorRT engines to improve inference performance on NVIDIA GPUs. It functions as a deep learning model optimizer and engine generator that converts neural network layers into high-performance runtime formats for hardware-accelerated graphics processors. The project features a custom layer conversion tool that allows users to define and register Python-based conversion logic to handle specialized operations not supported by default. This extensibility is paired with a registry-based system for mapping specific layer typ

This project is a comprehensive instructional resource and course for building neural networks using PyTorch. It covers the fundamental building blocks of deep learning, including tensor manipulation, automatic differentiation, and the construction of modular neural network components. The repository serves as a technical guide for several specialized domains. It provides implementation details for computer vision tasks such as image classification, object detection, and semantic segmentation, as well as natural language processing workflows involving transformers, recurrent networks, and gen

pytorch-OpCounter is a profiling utility for PyTorch neural networks designed to quantify model efficiency by calculating floating point operations and multiply-accumulate counts. It functions as a complexity analyzer to measure the computational cost and theoretical workload of different model architectures. The tool allows for the definition of custom operation counting rules to support third-party modules not covered by default. It uses forward hooks to intercept module calls and recursive traversal of the module tree to aggregate operations across child sub-modules. The project provides

Paddle is a deep learning framework designed for building, training, and deploying neural networks. It provides a platform for constructing models using tensor-based computations and supports both dynamic and static execution graphs to facilitate research and production workflows. The platform functions as a distributed machine learning system, enabling the scaling of training workloads across multiple nodes and hardware clusters. It includes a comprehensive toolkit for model deployment and optimization, allowing users to convert external model formats, compress trained models for resource-co

ComfyUI-Manager is an integrated utility designed to manage software dependencies, custom extensions, and machine learning assets within generative image workflow environments. It provides a centralized interface for the installation, update, and organization of third-party nodes and model files, ensuring that all necessary resources are available for processing tasks. The project distinguishes itself by automating the lifecycle of these components through both a graphical user interface and command-line utilities. It handles complex environment maintenance by fetching remote repositories, tr