The Best cONNXr Alternatives in 2026

Catniff provides JavaScript developers with a Torch-like deep learning framework.

Kubeflow provides a machine learning toolkit for deploying workflows on Kubernetes.

Build machine learning applications with Delta, an open-source framework implemented in Rust.

MLOps framework to package, deploy, monitor and manage thousands of production machine learning models.

Caffe provides an open framework for building and running deep learning models.

ONNX-MLIR compiles ONNX models using MLIR compiler infrastructure for model deployment workflows.

Tensors and Dynamic neural networks in Python with strong GPU acceleration.

Deep learning in Rust, with shape checked tensors and neural networks.

Infer.NET runs Bayesian inference in graphical models for a range of machine learning problems.

Cortex provides cloud infrastructure for deploying, managing, and scaling machine learning models in production.

Espresso AI uses machine learning to optimize Snowflake and Databricks data warehouses and reduce query and infrastructure costs.

PaddlePaddle provides a deep learning framework for training models across devices and platforms.

Colibri runs mixture-of-experts language models on local hardware, streaming experts from disk with a small C engine.

Glide provides an open model gateway for developing production generative AI applications.

Ollama runs language models locally and provides tools to work with model files and APIs.

Candle provides a minimalist Rust framework for machine learning model development and execution tasks.

DyNet provides tools for building dynamic neural networks and deep learning models.

Extensible Toolkit for Finetuning and Inference of Large Foundation Models.

Hugging Face Text Embeddings Inference serves text embedding models through an inference solution.

GPT-NeoX implements model parallel autoregressive transformers on GPUs using Megatron and DeepSpeed libraries.

This Docker-based starter kit provides a runtime for machine learning work in Jupyter notebooks.

MLX provides an array computing framework designed for Apple silicon devices.

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

The colibri-core NLP tool and library works with n-grams, skipgrams, and other linguistic patterns.