The cONNXr project provides a pure C runtime for ONNX models intended for embedded devices.
Open source
24 alternativesONNX-MLIR
ONNX-MLIR compiles ONNX models using MLIR compiler infrastructure for model deployment workflows.
About ONNX-MLIR
ONNX-MLIR is an open source compiler tool that transforms valid Open Neural Network Exchange (ONNX) graphs into executable code with minimal runtime support, built on LLVM/MLIR compiler infrastructure for model deployment workflows. It runs natively on Linux, macOS, and Windows, and provides prebuilt Docker containers to simplify setup, with current code generation support for generic CPUs and IBM's Telum integrated AI accelerator.
Key features
- Compiles valid ONNX graphs to executable code with minimal runtime
- Built on LLVM/MLIR compiler infrastructure
- Provides ONNX Dialect for integration in other projects
- Lowers ONNX graphs to MLIR files, LLVM bytecodes, C/Java libraries
- Includes onnx-mlir driver for lowering operations
- Offers Python, C, C++ runtime environments, optional Java support
Best for: It is most useful for developers and teams working on ONNX model deployment workflows who need compiler-based optimization and multi-language runtime support.
Good for
- Open source with community contribution support
- Runs natively on Linux, macOS, and Windows
- Prebuilt Docker containers simplify initial setup
Watch out for
- Non-Docker setup may require tricky dependency management on some systems
- Depends on a specific LLVM commit, requiring updates for newer LLVM levels
- Code generation support is currently limited to generic CPUs and IBM Telum AI accelerator
ONNX-MLIR at a glance
- Website
- github.com/onnx/onnx-mlir
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
ONNX-MLIR alternatives
Tools and sites you could use instead, ranked by how closely they match.
Kubeflow provides a machine learning toolkit for deploying workflows on Kubernetes.
Open source
24 alternatives
ClearML provides AI infrastructure for managing GPU clusters, machine learning workflows, and model deployment.
Colibri runs mixture-of-experts language models on local hardware, streaming experts from disk with a small C engine.
Open source
24 alternatives
Glide provides an open model gateway for developing production generative AI applications.
Open source
24 alternatives
Ollama runs language models locally and provides tools to work with model files and APIs.
Open source
24 alternativesPopular in AI Infrastructure & MLOps
Well-known listings from the same topic.
Guild AIguild.aiFlow AIflow-ai.comsystemprompt.iosystemprompt.ioCoreWeavecoreweave.comKili Technologykili-technology.comAPI docsdocs.x.ai
ONNX-MLIR FAQ
What operating systems support native ONNX-MLIR installation?
ONNX-MLIR runs natively on Linux, macOS, and Windows.
What is the recommended setup approach for ONNX-MLIR?
The preferred approach is using prebuilt Docker images and containers, as manual dependency setup can be complex on some systems.
What runtime environments does ONNX-MLIR provide?
It includes Python, C, C++ runtime environments, with optional Java support.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.