ML in Rust

11 pages in this section.

How Rust's ML crates share a tensor/computation-graph execution model, and why the ecosystem's goals - inference, embedding, safety - differ from Python's research-first design.

Explainer Rust Machine Learning Tensors

ML in Rust Basics

The landscape and where Rust fits.

Rust Ml In Rust Basics Machine Learning

candle

Hugging Face's minimalist Rust deep-learning framework.

Rust Ml In Rust Candle Deep Learning

burn

A flexible, backend-agnostic deep-learning framework.

Rust Ml In Rust Burn Training

ONNX Runtime (ort)

Running exported models fast.

Rust Ml In Rust Onnx Runtime

Tokenizers

The `tokenizers` crate for LLM pipelines.

Rust Ml In Rust Tokenizers Nlp

LLM Inference & Serving

Rust Ml In Rust Advanced Llm

Embeddings & Vector Search

Rust Ml In Rust Advanced Embeddings

GPU & Acceleration

Rust Ml In Rust Advanced Gpu

Serving Models with Axum

Production inference endpoints.

Rust Ml In Rust Serving Models

ML in Rust Best Practices

Reproducible, fast, memory-safe inference.

Rust Ml In Rust Best Practices List

ML in Rust

Search Documentation

ML in Rust