# microsoft/onnxruntime

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/microsoft-onnxruntime).**

19,347 stars · 3,710 forks · C++ · mit

## Links

- GitHub: https://github.com/microsoft/onnxruntime
- Homepage: https://onnxruntime.ai
- awesome-repositories: https://awesome-repositories.com/repository/microsoft-onnxruntime.md

## Topics

`ai-framework` `deep-learning` `hardware-acceleration` `machine-learning` `neural-networks` `onnx` `pytorch` `scikit-learn` `tensorflow`

## Description

This project is a cross-platform machine learning inference engine designed to execute pre-trained models across diverse operating systems and hardware environments. It functions as a standardized execution framework that manages the entire lifecycle of model inference, from loading and graph optimization to hardware-accelerated execution and generative sequence management.

The runtime distinguishes itself through a highly modular architecture that decouples model logic from hardware-specific kernels. By utilizing an execution provider abstraction, it enables developers to offload computations to specialized hardware such as GPUs, NPUs, and dedicated chipsets. It also provides a comprehensive toolkit for model optimization, including quantization, precision conversion, and graph-level transformations, which allow for significant reductions in binary size and latency for both edge and cloud deployments.

Beyond core inference, the project includes extensive support for generative AI, offering built-in capabilities for tokenization, chat template formatting, and streaming output generation. It supports complex model architectures through custom operator registration and modular adapter management, ensuring that developers can integrate specialized mathematical operations or fine-tuned model weights into their pipelines.

The software is built primarily in C++ and provides language-specific bindings to facilitate integration into various programming environments. It includes robust diagnostic and profiling tools that allow for granular performance analysis, hardware utilization tracking, and debugging of tensor data during the inference process.

## Tags

### Artificial Intelligence & ML

- [Cross-Platform Inference Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/cross-platform-inference-frameworks.md) — Enables consistent machine learning model execution across diverse operating systems and hardware architectures.
- [Hardware Acceleration](https://awesome-repositories.com/f/artificial-intelligence-ml/hardware-acceleration.md) — Offloads model computation to specialized hardware like GPUs and NPUs to improve inference speed. ([source](https://onnxruntime.ai/docs/build/))
- [Edge AI Model Deployment](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/local-and-on-device-inference/edge-ai-model-deployment.md) — Optimizes and deploys machine learning models for efficient execution on local edge and mobile hardware. ([source](https://onnxruntime.ai/docs/tutorials/))
- [ONNX Runtime Inference](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving/inference-engines/onnx-runtime-inference.md) — Executes pre-trained machine learning models using a standardized, cross-platform runtime for hardware-accelerated performance.
- [Generative AI Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-integrations.md) — Integrates generative AI capabilities including tokenization, chat templates, and streaming output into applications.
- [Generative AI Models](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-models.md) — Provides a framework for managing tokenization, chat templates, and streaming generation loops for large language models.
- [Machine Learning Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning-engines.md) — Enables building minimized, optimized inference engines by selecting specific operators and hardware providers.
- [Model Exporters](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/serialization-and-export-formats/model-exporters.md) — Converts trained machine learning models into standardized formats for high-performance cross-platform execution. ([source](https://onnxruntime.ai/docs/tutorials/azureml.html))
- [ONNX Model Exporters](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/serialization-and-export-formats/onnx-model-exporters.md) — Converts pre-trained machine learning models into the standardized ONNX format for cross-platform execution. ([source](https://onnxruntime.ai/docs/tutorials/accelerate-pytorch/resnet-inferencing.html))
- [Natural Language Processing](https://awesome-repositories.com/f/artificial-intelligence-ml/natural-language-processing.md) — Converts raw text into numerical sequences compatible with language models using standard vocabulary mapping and subword splitting. ([source](https://onnxruntime.ai/docs/tutorials/csharp/bert-nlp-csharp-console-app.html))
- [Provider Abstractions](https://awesome-repositories.com/f/artificial-intelligence-ml/provider-abstractions.md) — Normalizes diverse hardware-specific API schemas into a unified format to decouple model logic from hardware kernels.
- [Sequence Learning Models](https://awesome-repositories.com/f/artificial-intelligence-ml/sequence-learning-models.md) — Produces output sequences from a model based on provided generator parameters and the current model state. ([source](https://onnxruntime.ai/docs/genai/api/csharp.html))
- [Language Model Integrations](https://awesome-repositories.com/f/artificial-intelligence-ml/artificial-intelligence-tooling/language-model-integrations.md) — Provides language-specific bindings to execute pre-trained models within native applications. ([source](https://onnxruntime.ai/docs/get-started/community-projects.html))
- [Chat Template Management](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/decoding-generation-controls/chat-template-management.md) — Organizes input data into structured chat formats and enforces output schemas for conversational interaction and tool calling. ([source](https://onnxruntime.ai/docs/genai/))
- [Inference Execution Models](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving/engines-runtimes-servers/inference-execution-models.md) — Executes pre-trained machine learning models on mobile devices for real-time tasks like object detection. ([source](https://onnxruntime.ai/docs/tutorials/mobile/deploy-ios.html))
- [Model Inference Servers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-inference-serving/engines-runtimes-servers/model-inference-servers.md) — Hosts machine learning models in high-performance server environments to manage concurrent requests and optimize production throughput. ([source](https://onnxruntime.ai/docs/ecosystem/))
- [Tensor Operations](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-optimization-and-inference/hardware-and-acceleration/tensor-computing-libraries/tensor-operations.md) — Creates multi-dimensional arrays with specific shapes and data types to serve as inputs or outputs for model operations. ([source](https://onnxruntime.ai/docs/genai/api/java.html))
- [Model Adapters](https://awesome-repositories.com/f/artificial-intelligence-ml/model-adapters.md) — Switches between different fine-tuned model adapters at runtime to modify behavior dynamically without changing the base model. ([source](https://onnxruntime.ai/docs/genai/api/csharp.html))
- [Model Capability Extensions](https://awesome-repositories.com/f/artificial-intelligence-ml/model-capability-extensions.md) — Integrates custom mathematical operations and specialized computational layers into the inference engine to support non-standard model architectures. ([source](https://onnxruntime.ai/docs/get-started/with-javascript/react-native.html))
- [Model Execution Environments](https://awesome-repositories.com/f/artificial-intelligence-ml/model-execution-environments.md) — Runs generative inference loops including tokenization, model execution, and cache management. ([source](https://onnxruntime.ai/docs/genai/))
- [Model Graph Optimizers](https://awesome-repositories.com/f/artificial-intelligence-ml/model-graph-optimizers.md) — Simplifies and optimizes computational graphs by fusing operators and pruning redundant nodes to improve inference performance.
- [Model Optimization Toolkits](https://awesome-repositories.com/f/artificial-intelligence-ml/model-optimization-toolkits.md) — Offers a toolkit for model quantization, precision conversion, and graph-level transformations to improve inference performance.
- [Text Tokenizers](https://awesome-repositories.com/f/artificial-intelligence-ml/text-tokenizers.md) — Encodes input text into numerical sequences and decodes generated sequences back into human-readable text using specialized tokenization logic. ([source](https://onnxruntime.ai/docs/genai/api/c.html))
- [Data Preprocessing](https://awesome-repositories.com/f/artificial-intelligence-ml/data-preprocessing.md) — Transforms raw inputs like text or images into tensor formats required by models using integrated operators. ([source](https://onnxruntime.ai/docs/tutorials/web/build-web-app.html))
- [Model Deployment Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/deployment-pipelines-and-endpoints/model-deployment-pipelines.md) — Streamlines the development, optimization, and deployment of machine learning models using automated workflows. ([source](https://onnxruntime.ai/docs/ecosystem/))
- [Web-Based Model Deployment](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/deployment-pipelines-and-endpoints/web-based-model-deployment.md) — Generates web-based artifacts for browser-based model execution with hardware acceleration support. ([source](https://onnxruntime.ai/docs/build/web.html))
- [Machine Learning Model APIs](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-deployment-and-serving/inference-servers-and-runtimes/machine-learning-model-apis.md) — Executes models from common frameworks by converting them to a standardized format for cross-platform inference. ([source](https://onnxruntime.ai/docs/tutorials/traditional-ml.html))
- [Hardware Acceleration](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-optimization-and-inference/hardware-and-acceleration/hardware-acceleration.md) — Configures performance modes, precision, and memory strategies to balance inference latency and accuracy. ([source](https://onnxruntime.ai/docs/execution-providers/QNN-ExecutionProvider.html))
- [Model Loading](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/data-and-checkpointing/model-loading.md) — Initializes models from file paths to prepare them for inference and sequence generation. ([source](https://onnxruntime.ai/docs/genai/api/java.html))
- [Model Execution Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/model-execution-interfaces.md) — Provides a consistent programming API across languages and hardware to facilitate switching between acceleration backends. ([source](https://onnxruntime.ai/docs/execution-providers/))
- [On-Device Models](https://awesome-repositories.com/f/artificial-intelligence-ml/on-device-models.md) — Executes machine learning models on mobile devices using native interfaces for local inference. ([source](https://onnxruntime.ai/docs/get-started/with-obj-c.html))
- [Token Decoders](https://awesome-repositories.com/f/artificial-intelligence-ml/text-tokenizers/token-decoders.md) — Converts numerical token sequences or streams of tokens back into human-readable text strings for display. ([source](https://onnxruntime.ai/docs/genai/api/csharp.html))
- [Mixed Precision Training](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/machine-learning-training/distributed-and-accelerated-compute/training-acceleration-tools/mixed-precision-training.md) — Balances model accuracy and performance by automatically identifying and retaining critical operations in higher precision. ([source](https://onnxruntime.ai/docs/performance/model-optimizations/float16.html))
- [Model Performance Benchmarking](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-evaluation-analysis/model-analysis/model-performance-benchmarking.md) — Measures and compares the accuracy and latency of model inference across different execution environments and hardware backends to validate performance gains. ([source](https://onnxruntime.ai/docs/tutorials/accelerate-pytorch/resnet-inferencing.html))
- [Model Architecture](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/architecture-and-operations/model-architecture.md) — Configures metadata, tokenization, and structural submodules to ensure compatibility with specific generative and multi-modal model architectures. ([source](https://onnxruntime.ai/docs/genai/reference/config.html))
- [Model Fine-Tuning](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/fine-tuning-and-customization/model-fine-tuning.md) — Supports on-device model updates and fine-tuning through training-specific APIs and library compilation. ([source](https://onnxruntime.ai/docs/build/training.html))
- [Model Fine-Tuning and Adaptation](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/model-fine-tuning-adaptation.md) — Applies pre-compiled adapter binaries to model graphs for efficient task-specific adaptation during inference. ([source](https://onnxruntime.ai/docs/execution-providers/QNN-ExecutionProvider.html))
- [Sequence Encoders](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/speech-processing/sequence-to-sequence-tasks/sequence-encoders.md) — Transforms strings or batches of strings into numerical sequences compatible with model processing requirements. ([source](https://onnxruntime.ai/docs/genai/api/csharp.html))
- [Model Conversion Utilities](https://awesome-repositories.com/f/artificial-intelligence-ml/model-conversion-utilities.md) — Reduces model size and improves inference speed by casting floating-point operations to half-precision. ([source](https://onnxruntime.ai/docs/performance/model-optimizations/float16.html))
- [Model Quantization](https://awesome-repositories.com/f/artificial-intelligence-ml/model-quantization.md) — Matches weights and activation tensors between original and quantized models to resolve precision loss. ([source](https://onnxruntime.ai/docs/performance/model-optimizations/quantization.html))
- [On-Device Inference Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/on-device-inference-engines.md) — Supports on-device training and local adaptation of machine learning models on edge hardware. ([source](https://onnxruntime.ai/docs/get-started/with-cpp.html))
- [Tensor Data Accessors](https://awesome-repositories.com/f/artificial-intelligence-ml/tensor-data-accessors.md) — Provides direct access to tensor memory, shapes, and data types for custom input and output manipulation. ([source](https://onnxruntime.ai/docs/genai/api/cpp.html))
- [Chat State Management](https://awesome-repositories.com/f/artificial-intelligence-ml/chat-state-management.md) — Maintains conversational state by iteratively appending user input to token sequences for continuous model interaction. ([source](https://onnxruntime.ai/docs/genai/howto/migrate.html))
- [Chat Generation Strategies](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/decoding-generation-controls/chat-generation-strategies.md) — Applies search algorithms and sampling methods like TopP or TopK to manage output generation. ([source](https://onnxruntime.ai/docs/genai/))
- [Generation Controls](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/decoding-generation-controls/generation-controls.md) — Adjusts search strategies and guidance settings to control model behavior and influence generated output. ([source](https://onnxruntime.ai/docs/genai/api/c.html))
- [Hardware Acceleration Backends](https://awesome-repositories.com/f/artificial-intelligence-ml/hardware-acceleration-backends.md) — Checks for the availability of specific hardware backends to determine if accelerated model execution is supported on the current device. ([source](https://onnxruntime.ai/docs/genai/api/python.html))
- [Model Inference Runtimes](https://awesome-repositories.com/f/artificial-intelligence-ml/model-inference-runtimes.md) — Encapsulates external models or inference engines within custom operators to integrate third-party formats. ([source](https://onnxruntime.ai/docs/reference/operators/add-custom-op.html))
- [Performance Profilers](https://awesome-repositories.com/f/artificial-intelligence-ml/model-optimization/profiling-and-benchmarking/performance-profilers.md) — Analyzes model performance by identifying computational bottlenecks and measuring the time spent on individual operators or subgraphs during inference. ([source](https://onnxruntime.ai/docs/performance/transformers-optimization.html))
- [Model Output Formatting](https://awesome-repositories.com/f/artificial-intelligence-ml/model-output-formatting.md) — Processes raw model results into application-specific formats for use in user interfaces. ([source](https://onnxruntime.ai/docs/tutorials/web/build-web-app.html))
- [Model Training Optimizers](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training-optimizers.md) — Provides pre-configured environments with optimized libraries to accelerate model execution and deployment on cloud infrastructure. ([source](https://onnxruntime.ai/docs/ecosystem/acpt.html))

### Scientific & Mathematical Computing

- [Graph-Based Execution Engines](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/scientific-computing-platforms/graph-based-execution-engines.md) — Optimizes and executes machine learning models by representing them as directed acyclic graphs of tensors and operators.

### Software Engineering & Architecture

- [Cross-Platform Runtimes](https://awesome-repositories.com/f/software-engineering-architecture/cross-platform-runtimes.md) — Provides a cross-platform runtime environment for executing machine learning models consistently across diverse hardware and operating systems. ([source](https://onnxruntime.ai/docs/reference/compatibility.html))

### Data & Databases

- [Token Streamers](https://awesome-repositories.com/f/data-databases/data-processing-pipelines/stream-processing-systems/data-streaming/real-time-stream-monitors/token-stream-interceptors/token-streamers.md) — Delivers generated tokens incrementally to the user interface as they are produced to provide real-time feedback. ([source](https://onnxruntime.ai/docs/genai/tutorials/phi2-python.html))
- [Operator Registries](https://awesome-repositories.com/f/data-databases/custom-driver-registration/operator-registries.md) — Adds user-defined operations to the engine by linking shared libraries or calling registration functions. ([source](https://onnxruntime.ai/docs/extensions/))

### DevOps & Infrastructure

- [Inference Engine Compilers](https://awesome-repositories.com/f/devops-infrastructure/inference-engine-compilers.md) — Supports building custom, hardware-specific inference engines from source to optimize performance for target environments. ([source](https://onnxruntime.ai/docs/build/))
- [Cloud Deployment](https://awesome-repositories.com/f/devops-infrastructure/cloud-deployment.md) — Packages machine learning models and scoring logic into scalable web services to provide real-time predictions via network requests. ([source](https://onnxruntime.ai/docs/tutorials/azureml.html))
- [Cloud Infrastructure Deployment](https://awesome-repositories.com/f/devops-infrastructure/cloud-infrastructure-deployment.md) — Executes machine learning models within managed cloud environments and containerized services to scale inference across distributed systems. ([source](https://onnxruntime.ai/docs/ecosystem/))
- [Model Conversion](https://awesome-repositories.com/f/devops-infrastructure/model-conversion.md) — Transforms machine learning models into optimized formats for high-performance execution across diverse hardware. ([source](https://onnxruntime.ai/docs/genai/howto/build-model.html))
- [Deployment Targets](https://awesome-repositories.com/f/devops-infrastructure/deployment-management-strategies/execution-platforms-and-targets/deployment-targets.md) — Compiles the library for mobile and web browser environments to ensure compatibility with diverse deployment targets. ([source](https://onnxruntime.ai/docs/build/))
- [Runtime Configurations](https://awesome-repositories.com/f/devops-infrastructure/storage-backend-configurations/runtime-configurations.md) — Accesses backend-specific settings and hardware properties through structured configuration strings to tune performance for specific environments. ([source](https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html))
- [Android Packages](https://awesome-repositories.com/f/devops-infrastructure/distribution-packaging/software-distribution/application-packaging/android-packages.md) — Generates archive files from model definitions to enable direct integration and deployment within mobile development environments. ([source](https://onnxruntime.ai/docs/build/android.html))
- [Windows Deployment Utilities](https://awesome-repositories.com/f/devops-infrastructure/windows-deployment-utilities.md) — Facilitates native machine learning model execution on Windows using platform-specific or cross-platform interfaces. ([source](https://onnxruntime.ai/docs/get-started/with-windows.html))

### Operating Systems & Systems Programming

- [GPU Acceleration](https://awesome-repositories.com/f/operating-systems-systems-programming/hardware-interfacing-drivers/hardware-acceleration/gpu-acceleration.md) — Offloads model computation to NVIDIA graphics hardware to increase throughput and reduce latency. ([source](https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html))
- [Hardware Acceleration](https://awesome-repositories.com/f/operating-systems-systems-programming/hardware-interfacing-drivers/hardware-acceleration.md) — Integrates custom hardware acceleration by implementing standardized interfaces that delegate sub-graph execution to specific devices. ([source](https://onnxruntime.ai/docs/execution-providers/))
- [Chipset Acceleration](https://awesome-repositories.com/f/operating-systems-systems-programming/hardware-interfacing-drivers/hardware-acceleration/chipset-acceleration.md) — Executes models on mobile or embedded chipsets by offloading computation to dedicated processor cores. ([source](https://onnxruntime.ai/docs/execution-providers/QNN-ExecutionProvider.html))
- [Arena Allocators](https://awesome-repositories.com/f/operating-systems-systems-programming/kernel-core-internals/process-and-memory-management/memory-management/allocation-strategies/dynamic-memory-allocation/arena-allocators.md) — Manages tensor memory through pre-allocated pools to eliminate costly runtime allocations during iterative inference loops.
- [Binary Swapping Utilities](https://awesome-repositories.com/f/operating-systems-systems-programming/systems-programming/runtime-libraries/binary-swapping-utilities.md) — Enables the replacement of default library implementations with custom builds to support specific hardware execution providers. ([source](https://onnxruntime.ai/docs/get-started/with-windows.html))

### System Administration & Monitoring

- [Operation Execution](https://awesome-repositories.com/f/system-administration-monitoring/server-operational-management/operation-execution.md) — Processes models using a wide range of standardized operator sets and supports custom operator execution. ([source](https://onnxruntime.ai/docs/reference/compatibility.html))

### Development Tools & Productivity

- [Custom Operator Interfaces](https://awesome-repositories.com/f/development-tools-productivity/developer-utilities-libraries/extensibility-frameworks/custom-operator-interfaces.md) — Provides mechanisms for registering and integrating user-defined mathematical operations into the core computation pipeline. ([source](https://onnxruntime.ai/docs/extensions/add-op.html))
- [Cross-Platform Build Targets](https://awesome-repositories.com/f/development-tools-productivity/cross-platform-build-targets.md) — Supports cross-compilation and native builds for specialized hardware platforms, including non-x86 architectures. ([source](https://onnxruntime.ai/docs/build/inferencing.html))
- [Bundle Size Optimization](https://awesome-repositories.com/f/development-tools-productivity/bundle-size-optimization.md) — Minimizes binary footprint by including only necessary operators for specific model requirements. ([source](https://onnxruntime.ai/docs/install/))
- [Operator Packages](https://awesome-repositories.com/f/development-tools-productivity/dependency-managers/python-packages/operator-packages.md) — Bundles specialized machine learning operations into installable packages for Python, Java, and other environments. ([source](https://onnxruntime.ai/docs/extensions/build.html))
- [Library Packaging Tools](https://awesome-repositories.com/f/development-tools-productivity/library-packaging-tools.md) — Generates custom-built library packages for mobile platforms to support optimized native application integration. ([source](https://onnxruntime.ai/docs/build/custom.html))

### Programming Languages & Runtimes

- [Language Bindings](https://awesome-repositories.com/f/programming-languages-runtimes/language-interoperability/language-bindings.md) — Generates native language interfaces to enable model execution within diverse programming environments. ([source](https://onnxruntime.ai/docs/build/inferencing.html))
- [Deployment-Specific Runtimes](https://awesome-repositories.com/f/programming-languages-runtimes/runtime-execution-environments/runtime-environments/runtimes/deployment-specific-runtimes.md) — Enables the creation of minimized, deployment-specific inference runtimes tailored to constrained environments or specific models. ([source](https://onnxruntime.ai/docs/tutorials/accelerate-pytorch/pytorch.html))
- [Python Bindings](https://awesome-repositories.com/f/programming-languages-runtimes/language-interoperability/interoperability/python-bindings.md) — Provides native integration layers for Python environments to facilitate model execution. ([source](https://onnxruntime.ai/docs/build/custom.html))
- [Integer Conversion Utilities](https://awesome-repositories.com/f/programming-languages-runtimes/programming-utilities/data-structure-type-helpers/data-type-utilities/integer-conversion-utilities.md) — Reduces model size and accelerates inference by mapping 32-bit floating point values to lower-precision integer representations. ([source](https://onnxruntime.ai/docs/performance/model-optimizations/quantization.html))
- [Cross-Language Bindings Layers](https://awesome-repositories.com/f/programming-languages-runtimes/language-interoperability/foreign-function-interfaces/cross-language-bindings-layers.md) — Provides bridging mechanisms to map low-level C interfaces to multiple programming languages for consistent model execution.

### Security & Cryptography

- [Executable Footprint Optimizers](https://awesome-repositories.com/f/security-cryptography/secret-footprint-minimization/executable-footprint-optimizers.md) — Customizes the set of included operator kernels during the build process to reduce the final executable footprint. ([source](https://onnxruntime.ai/docs/build/custom.html))

### User Interface & Experience

- [Multimodal Input Processors](https://awesome-repositories.com/f/user-interface-experience/form-and-input-management/input-handling/multimodal-input-processors.md) — Loads and processes image and audio data into tensors for use as inputs within generative model inference pipelines. ([source](https://onnxruntime.ai/docs/genai/api/c.html))

### Web Development

- [Context Binaries](https://awesome-repositories.com/f/web-development/webassembly-compilation/binary-optimizers/context-binaries.md) — Converts models into optimized context binaries tailored for specific hardware architectures. ([source](https://onnxruntime.ai/docs/genai/howto/build-models-for-snapdragon.html))