
onnxruntime-genai
Generative AI extensions for onnxruntime
Stars: 829

ONNX Runtime Generative AI is a library that provides the generative AI loop for ONNX models, including inference with ONNX Runtime, logits processing, search and sampling, and KV cache management. Users can call a high level `generate()` method, or run each iteration of the model in a loop. It supports greedy/beam search and TopP, TopK sampling to generate token sequences, has built in logits processing like repetition penalties, and allows for easy custom scoring.
README:
Note: between 0.9.0 and the 0.8.3 release, there is a breaking API change. Previously, the inputs for non-LLMs would be set with params.SetInputs(inputs)
. Now, inputs for non-LLMs are set with generator.SetInputs(inputs)
. With this change, inputs for all models and their modalities are set on the generator
instead of the generatorParams
. The inputs for LLMs are set with generator.append_tokens(tokens)
and the inputs for non-LLMs are set with generator.SetInputs(inputs)
.
Run generative AI models with ONNX Runtime.
This API gives you an easy, flexible and performant way of running LLMs on device.
It implements the generative AI loop for ONNX models, including pre and post processing, inference with ONNX Runtime, logits processing, search and sampling, and KV cache management.
See documentation at https://onnxruntime.ai/docs/genai.
Support matrix | Supported now | Under development | On the roadmap |
---|---|---|---|
Model architectures | AMD OLMo ChatGLM DeepSeek ERNIE 4.5 Gemma gpt-oss Granite Llama * Mistral + Nemotron Phi (language + vision) Qwen SmolLM3 |
Whisper | Stable diffusion |
API | Python C# C/C++ Java ^ |
Objective-C | |
Platform | Linux Windows Mac ^ Android ^ |
iOS | |
Architecture | x86 x64 Arm64 ~ |
||
Hardware Acceleration | CUDA DirectML |
QNN OpenVINO ROCm |
NvTensorRtRtx |
Features | MultiLoRA Continuous decoding (session continuation)^ |
Constrained decoding | Speculative decoding |
* The Llama model architecture supports similar model families such as CodeLlama, Vicuna, Yi, and more.
+ The Mistral model architecture supports similar model families such as Zephyr.
^ Requires build from source
~ Windows builds available, requires build from source for other platforms
See installation instructions or build from source
-
Download the model
huggingface-cli download microsoft/Phi-3-mini-4k-instruct-onnx --include cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4/* --local-dir .
-
Install the API
pip install numpy pip install --pre onnxruntime-genai
-
Run the model
import onnxruntime_genai as og model = og.Model('cpu_and_mobile/cpu-int4-rtn-block-32-acc-level-4') tokenizer = og.Tokenizer(model) tokenizer_stream = tokenizer.create_stream() # Set the max length to something sensible by default, # since otherwise it will be set to the entire context length search_options = {} search_options['max_length'] = 2048 search_options['batch_size'] = 1 chat_template = '<|user|>\n{input} <|end|>\n<|assistant|>' text = input("Input: ") if not text: print("Error, input cannot be empty") exit prompt = f'{chat_template.format(input=text)}' input_tokens = tokenizer.encode(prompt) params = og.GeneratorParams(model) params.set_search_options(**search_options) generator = og.Generator(model, params) print("Output: ", end='', flush=True) try: generator.append_tokens(input_tokens) while not generator.is_done(): generator.generate_next_token() new_token = generator.get_next_tokens()[0] print(tokenizer_stream.decode(new_token), end='', flush=True) except KeyboardInterrupt: print(" --control+c pressed, aborting generation--") print() del generator
Due to evolving nature of this project and ongoing feature additions, examples in the main
branch may not always align with the latest stable release. This section outlines how to ensure compatibility between the examples and the corresponding version. Majority of the steps would remain same, just the package installation and the model example file would change.
Install the package according to the installation instructions. Let's say you installed 0.5.2 version of ONNX Runtime GenAI, so the instructions would look like this:
# Clone the repo
git clone https://github.com/microsoft/onnxruntime-genai.git && cd onnxruntime-genai
# Checkout the branch for the version you are using
git checkout v0.5.2
cd examples
Build the package from source using these instructions. Now just go to the folder location where all the examples are present.
# Clone the repo
git clone https://github.com/microsoft/onnxruntime-genai.git && cd onnxruntime-genai
cd examples
See the Discussions to request new features and up-vote existing requests.
This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for onnxruntime-genai
Similar Open Source Tools

onnxruntime-genai
ONNX Runtime Generative AI is a library that provides the generative AI loop for ONNX models, including inference with ONNX Runtime, logits processing, search and sampling, and KV cache management. Users can call a high level `generate()` method, or run each iteration of the model in a loop. It supports greedy/beam search and TopP, TopK sampling to generate token sequences, has built in logits processing like repetition penalties, and allows for easy custom scoring.

Trace
Trace is a new AutoDiff-like tool for training AI systems end-to-end with general feedback. It generalizes the back-propagation algorithm by capturing and propagating an AI system's execution trace. Implemented as a PyTorch-like Python library, users can write Python code directly and use Trace primitives to optimize certain parts, similar to training neural networks.

magika
Magika is a novel AI-powered file type detection tool that relies on deep learning to provide accurate detection. It employs a custom, highly optimized model to enable precise file identification within milliseconds. Trained on a dataset of ~100M samples across 200+ content types, achieving an average ~99% accuracy. Used at scale by Google to improve user safety by routing files to security scanners. Available as a command line tool in Rust, Python API, and bindings for Rust, JavaScript/TypeScript, and GoLang.

cuvs
cuVS is a library that contains state-of-the-art implementations of several algorithms for running approximate nearest neighbors and clustering on the GPU. It can be used directly or through the various databases and other libraries that have integrated it. The primary goal of cuVS is to simplify the use of GPUs for vector similarity search and clustering.

lotus
LOTUS (LLMs Over Tables of Unstructured and Structured Data) is a query engine that provides a declarative programming model and an optimized query engine for reasoning-based query pipelines over structured and unstructured data. It offers a simple and intuitive Pandas-like API with semantic operators for fast and easy LLM-powered data processing. The tool implements a semantic operator programming model, allowing users to write AI-based pipelines with high-level logic and leaving the rest of the work to the query engine. LOTUS supports various semantic operators like sem_map, sem_filter, sem_extract, sem_agg, sem_topk, sem_join, sem_sim_join, and sem_search, enabling users to perform tasks like mapping records, filtering data, aggregating records, and more. The tool also supports different model classes such as LM, RM, and Reranker for language modeling, retrieval, and reranking tasks respectively.

MPLSandbox
MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for LLMs. It simplifies code analysis for researchers and can be seamlessly integrated into LLM training and application processes to enhance performance in a range of code-related tasks. The sandbox environment ensures safe code execution, the code analysis module offers comprehensive analysis reports, and the information integration module combines compilation feedback and analysis results for complex code-related tasks.

poml
POML (Prompt Orchestration Markup Language) is a novel markup language designed to bring structure, maintainability, and versatility to advanced prompt engineering for Large Language Models (LLMs). It addresses common challenges in prompt development, such as lack of structure, complex data integration, format sensitivity, and inadequate tooling. POML provides a systematic way to organize prompt components, integrate diverse data types seamlessly, and manage presentation variations, empowering developers to create more sophisticated and reliable LLM applications.

yalm
Yalm (Yet Another Language Model) is an LLM inference implementation in C++/CUDA, emphasizing performance engineering, documentation, scientific optimizations, and readability. It is not for production use and has been tested on Mistral-v0.2 and Llama-3.2. Requires C++20-compatible compiler, CUDA toolkit, and LLM safetensor weights in huggingface format converted to .yalm file.

ArcticTraining
ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs). It offers modular trainer designs, simplified code structures, and integrated pipelines for creating and cleaning synthetic data, enabling users to enhance LLM capabilities like code generation and complex reasoning with greater efficiency and flexibility.

codellm-devkit
Codellm-devkit (CLDK) is a Python library that serves as a multilingual program analysis framework bridging traditional static analysis tools and Large Language Models (LLMs) specialized for code (CodeLLMs). It simplifies the process of analyzing codebases across multiple programming languages, enabling the extraction of meaningful insights and facilitating LLM-based code analysis. The library provides a unified interface for integrating outputs from various analysis tools and preparing them for effective use by CodeLLMs. Codellm-devkit aims to enable the development and experimentation of robust analysis pipelines that combine traditional program analysis tools and CodeLLMs, reducing friction in multi-language code analysis and ensuring compatibility across different tools and LLM platforms. It is designed to seamlessly integrate with popular analysis tools like WALA, Tree-sitter, LLVM, and CodeQL, acting as a crucial intermediary layer for efficient communication between these tools and CodeLLMs. The project is continuously evolving to include new tools and frameworks, maintaining its versatility for code analysis and LLM integration.

llm-analysis
llm-analysis is a tool designed for Latency and Memory Analysis of Transformer Models for Training and Inference. It automates the calculation of training or inference latency and memory usage for Large Language Models (LLMs) or Transformers based on specified model, GPU, data type, and parallelism configurations. The tool helps users to experiment with different setups theoretically, understand system performance, and optimize training/inference scenarios. It supports various parallelism schemes, communication methods, activation recomputation options, data types, and fine-tuning strategies. Users can integrate llm-analysis in their code using the `LLMAnalysis` class or use the provided entry point functions for command line interface. The tool provides lower-bound estimations of memory usage and latency, and aims to assist in achieving feasible and optimal setups for training or inference.

AIF360
The AI Fairness 360 toolkit is an open-source library designed to detect and mitigate bias in machine learning models. It provides a comprehensive set of metrics, explanations, and algorithms for bias mitigation in various domains such as finance, healthcare, and education. The toolkit supports multiple bias mitigation algorithms and fairness metrics, and is available in both Python and R. Users can leverage the toolkit to ensure fairness in AI applications and contribute to its development for extensibility.

sports-betting
Sports-betting is a Python library for implementing betting strategies and analyzing sports data. It provides tools for collecting, processing, and visualizing sports data to make informed betting decisions. The library includes modules for scraping data from sports websites, calculating odds, simulating betting strategies, and evaluating performance. With sports-betting, users can automate betting processes, test different strategies, and improve their betting outcomes.

agents
Polymarket Agents is a developer framework and set of utilities for building AI agents to trade autonomously on Polymarket. It integrates with Polymarket API, provides AI agent utilities for prediction markets, supports local and remote RAG, sources data from various services, and offers comprehensive LLM tools for prompt engineering. The architecture features modular components like APIs and scripts for managing local environments, server set-up, and CLI for end-user commands.

RAVE
RAVE is a variational autoencoder for fast and high-quality neural audio synthesis. It can be used to generate new audio samples from a given dataset, or to modify the style of existing audio samples. RAVE is easy to use and can be trained on a variety of audio datasets. It is also computationally efficient, making it suitable for real-time applications.

habitat-lab
Habitat-Lab is a modular high-level library for end-to-end development in embodied AI. It is designed to train agents to perform a wide variety of embodied AI tasks in indoor environments, as well as develop agents that can interact with humans in performing these tasks.
For similar tasks

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

ai-guide
This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

onnxruntime-genai
ONNX Runtime Generative AI is a library that provides the generative AI loop for ONNX models, including inference with ONNX Runtime, logits processing, search and sampling, and KV cache management. Users can call a high level `generate()` method, or run each iteration of the model in a loop. It supports greedy/beam search and TopP, TopK sampling to generate token sequences, has built in logits processing like repetition penalties, and allows for easy custom scoring.

jupyter-ai
Jupyter AI connects generative AI with Jupyter notebooks. It provides a user-friendly and powerful way to explore generative AI models in notebooks and improve your productivity in JupyterLab and the Jupyter Notebook. Specifically, Jupyter AI offers: * An `%%ai` magic that turns the Jupyter notebook into a reproducible generative AI playground. This works anywhere the IPython kernel runs (JupyterLab, Jupyter Notebook, Google Colab, Kaggle, VSCode, etc.). * A native chat UI in JupyterLab that enables you to work with generative AI as a conversational assistant. * Support for a wide range of generative model providers, including AI21, Anthropic, AWS, Cohere, Gemini, Hugging Face, NVIDIA, and OpenAI. * Local model support through GPT4All, enabling use of generative AI models on consumer grade machines with ease and privacy.

khoj
Khoj is an open-source, personal AI assistant that extends your capabilities by creating always-available AI agents. You can share your notes and documents to extend your digital brain, and your AI agents have access to the internet, allowing you to incorporate real-time information. Khoj is accessible on Desktop, Emacs, Obsidian, Web, and Whatsapp, and you can share PDF, markdown, org-mode, notion files, and GitHub repositories. You'll get fast, accurate semantic search on top of your docs, and your agents can create deeply personal images and understand your speech. Khoj is self-hostable and always will be.

langchain_dart
LangChain.dart is a Dart port of the popular LangChain Python framework created by Harrison Chase. LangChain provides a set of ready-to-use components for working with language models and a standard interface for chaining them together to formulate more advanced use cases (e.g. chatbots, Q&A with RAG, agents, summarization, extraction, etc.). The components can be grouped into a few core modules: * **Model I/O:** LangChain offers a unified API for interacting with various LLM providers (e.g. OpenAI, Google, Mistral, Ollama, etc.), allowing developers to switch between them with ease. Additionally, it provides tools for managing model inputs (prompt templates and example selectors) and parsing the resulting model outputs (output parsers). * **Retrieval:** assists in loading user data (via document loaders), transforming it (with text splitters), extracting its meaning (using embedding models), storing (in vector stores) and retrieving it (through retrievers) so that it can be used to ground the model's responses (i.e. Retrieval-Augmented Generation or RAG). * **Agents:** "bots" that leverage LLMs to make informed decisions about which available tools (such as web search, calculators, database lookup, etc.) to use to accomplish the designated task. The different components can be composed together using the LangChain Expression Language (LCEL).

danswer
Danswer is an open-source Gen-AI Chat and Unified Search tool that connects to your company's docs, apps, and people. It provides a Chat interface and plugs into any LLM of your choice. Danswer can be deployed anywhere and for any scale - on a laptop, on-premise, or to cloud. Since you own the deployment, your user data and chats are fully in your own control. Danswer is MIT licensed and designed to be modular and easily extensible. The system also comes fully ready for production usage with user authentication, role management (admin/basic users), chat persistence, and a UI for configuring Personas (AI Assistants) and their Prompts. Danswer also serves as a Unified Search across all common workplace tools such as Slack, Google Drive, Confluence, etc. By combining LLMs and team specific knowledge, Danswer becomes a subject matter expert for the team. Imagine ChatGPT if it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already supported?" or "Where's the pull request for feature Y?"

infinity
Infinity is an AI-native database designed for LLM applications, providing incredibly fast full-text and vector search capabilities. It supports a wide range of data types, including vectors, full-text, and structured data, and offers a fused search feature that combines multiple embeddings and full text. Infinity is easy to use, with an intuitive Python API and a single-binary architecture that simplifies deployment. It achieves high performance, with 0.1 milliseconds query latency on million-scale vector datasets and up to 15K QPS.
For similar jobs

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.