<div align="center">
<h1>mlxrs</h1>
</div>
<div align="center">
Safe Rust bindings for Apple MLX — core arrays & ops, plus LM, VLM, audio, and embeddings
[<img alt="github" src="https://img.shields.io/badge/github-findit--ai/mlxrs-8da0cb?style=for-the-badge&logo=Github" height="22">][Github-url]
<img alt="LoC" src="https://img.shields.io/endpoint?url=https%3A%2F%2Fgist.githubusercontent.com%2Fal8n%2F327b2a8aef9003246e45c6e47fe63937%2Fraw%2Fmlxrs" height="22">
[<img alt="Build" src="https://img.shields.io/github/actions/workflow/status/findit-ai/mlxrs/mlxrs.yml?logo=Github-Actions&style=for-the-badge" height="22">][CI-url]
[<img alt="codecov" src="https://img.shields.io/codecov/c/gh/findit-ai/mlxrs?style=for-the-badge&token=6R3QFWRWHL&logo=codecov" height="22">][codecov-url]
[<img alt="docs.rs" src="https://img.shields.io/badge/docs.rs-mlxrs-66c2a5?style=for-the-badge&labelColor=555555&logo=data:image/svg+xml;base64,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" height="20">][doc-url]
[<img alt="crates.io" src="https://img.shields.io/crates/v/mlxrs?style=for-the-badge&logo=data:image/svg+xml;base64,PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0iaXNvLTg4NTktMSI/Pg0KPCEtLSBHZW5lcmF0b3I6IEFkb2JlIElsbHVzdHJhdG9yIDE5LjAuMCwgU1ZHIEV4cG9ydCBQbHVnLUluIC4gU1ZHIFZlcnNpb246IDYuMDAgQnVpbGQgMCkgIC0tPg0KPHN2ZyB2ZXJzaW9uPSIxLjEiIGlkPSJMYXllcl8xIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciIHhtbG5zOnhsaW5rPSJodHRwOi8vd3d3LnczLm9yZy8xOTk5L3hsaW5rIiB4PSIwcHgiIHk9IjBweCINCgkgdmlld0JveD0iMCAwIDUxMiA1MTIiIHhtbDpzcGFjZT0icHJlc2VydmUiPg0KPGc+DQoJPGc+DQoJCTxwYXRoIGQ9Ik0yNTYsMEwzMS41MjgsMTEyLjIzNnYyODcuNTI4TDI1Niw1MTJsMjI0LjQ3Mi0xMTIuMjM2VjExMi4yMzZMMjU2LDB6IE0yMzQuMjc3LDQ1Mi41NjRMNzQuOTc0LDM3Mi45MTNWMTYwLjgxDQoJCQlsMTU5LjMwMyw3OS42NTFWNDUyLjU2NHogTTEwMS44MjYsMTI1LjY2MkwyNTYsNDguNTc2bDE1NC4xNzQsNzcuMDg3TDI1NiwyMDIuNzQ5TDEwMS44MjYsMTI1LjY2MnogTTQzNy4wMjYsMzcyLjkxMw0KCQkJbC0xNTkuMzAzLDc5LjY1MVYyNDAuNDYxbDE1OS4zMDMtNzkuNjUxVjM3Mi45MTN6IiBmaWxsPSIjRkZGIi8+DQoJPC9nPg0KPC9nPg0KPGc+DQo8L2c+DQo8Zz4NCjwvZz4NCjxnPg0KPC9nPg0KPGc+DQo8L2c+DQo8Zz4NCjwvZz4NCjxnPg0KPC9nPg0KPGc+DQo8L2c+DQo8Zz4NCjwvZz4NCjxnPg0KPC9nPg0KPGc+DQo8L2c+DQo8Zz4NCjwvZz4NCjxnPg0KPC9nPg0KPGc+DQo8L2c+DQo8Zz4NCjwvZz4NCjxnPg0KPC9nPg0KPC9zdmc+DQo=" height="22">][crates-url]
[<img alt="crates.io" src="https://img.shields.io/crates/d/mlxrs?color=critical&logo=data:image/svg+xml;base64,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&style=for-the-badge" height="22">][crates-url]
<img alt="license" src="https://img.shields.io/badge/License-Apache%202.0/MIT-blue.svg?style=for-the-badge&fontColor=white&logoColor=f5c076&logo=data:image/svg+xml;base64,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" height="22">
</div>
## Overview
`mlxrs` provides safe, idiomatic Rust bindings to [MLX](https://github.com/ml-explore/mlx) —
Apple's array framework for machine learning on Apple silicon — through the
[`mlx-c`](https://github.com/ml-explore/mlx-c) FFI layer. As in MLX, operations build a
**lazy** computation graph and run only when a result is read (`to_vec`, `item`) or
`eval` is called, preserving the unified-memory CPU/GPU execution model.
On top of the core `Array` / `Dtype` / `ops` surface, optional features port the
higher-level support of MLX's companion projects — `mlx-lm`, `mlx-vlm`, `mlx-audio`,
and `mlx-embeddings` (loaders, tokenizers, KV-caches, samplers, quantization,
generation loops, audio DSP, pooling).
## Installation
Core only:
```toml
[dependencies]
mlxrs = "0.1"
```
Or enable one of the higher-level feature sets:
```toml
# language models
[dependencies]
mlxrs = { version = "0.1", features = ["lm"] }
```
```toml
# vision-language models (implies lm)
[dependencies]
mlxrs = { version = "0.1", features = ["vlm"] }
```
```toml
# audio (implies lm)
[dependencies]
mlxrs = { version = "0.1", features = ["audio"] }
```
```toml
# embedding utilities
[dependencies]
mlxrs = { version = "0.1", features = ["embeddings"] }
```
## Quick start
```rust
use mlxrs::Array;
fn main() -> mlxrs::Result<()> {
let a = Array::from_slice::<f32>(&[1.0, 2.0, 3.0], &[3])?;
let b = Array::from_slice::<f32>(&[10.0, 20.0, 30.0], &[3])?;
// Ops build a lazy graph; reading the result forces evaluation.
let mut c = a.add(&b)?;
assert_eq!(c.to_vec::<f32>()?, vec![11.0, 22.0, 33.0]);
Ok(())
}
```
The fallible `a.add(&b)?` form is always available; operator overloads
(`&a + &b`) are opt-in behind `unstable-ops-overload` (see Caveats).
## Features
Higher-level surfaces are off by default — enable what you need:
- **`lm`** — language models: tokenizers (BPE / SPM / chat templates / tool
parsing), KV-caches, samplers + logits processors, quantization, LoRA/DoRA,
optimizers, and the generation loop.
- **`vlm`** — vision-language models (implies `lm`): image preprocessing, prompt
assembly, multimodal generation.
- **`audio`** — audio (implies `lm`): STFT/mel DSP, WAV I/O, STT/TTS, playback.
- **`embeddings`** — embedding-model loading, pooling, and the encode pipeline.
Finer-grained flags (individual `tokenizer-*`, `gguf`, `llguidance`,
`unstable-ops-overload`) are listed in [`mlxrs/Cargo.toml`](mlxrs/Cargo.toml) and
the [API docs][doc-url].
## Platform support
mlxrs targets `aarch64-apple-darwin` (Apple silicon). Other platforms
(`x86_64-apple-darwin`, Linux + CUDA, distributed) are roadmapped.
## Caveats
- **`Array` is `!Send` and `!Sync`** — single-thread use only. The underlying
C++ `array_desc` is shared by `Array::try_clone` (refcount-bumped) and
mutates non-atomic state internally, so cross-thread sharing is unsound
without external synchronization. `Array` does **not** implement `Clone`;
the only duplication is the fallible `try_clone`. There is no shared-array
wrapper — to use array data on another thread, extract owned data via
`to_vec` / `item` (which yield `Send` values) and move that.
- **GPU work is single-stream serialized per thread** — the internal
default-stream is per-thread and maps to one Metal command queue per
thread. mlxrs exposes a public `Stream`/`Device` API; note `Stream` is a
**thread-affine, non-RAII handle**: it is `!Send + !Sync`, `Drop` frees
only the mlx-c handle box (mlx has no per-stream teardown), and
`Stream::new_on` permanently grows mlx's process-global stream state — so
allocate a *bounded* set at startup, never per request/task. The only
reclaim path is the bulk, end-of-thread `Stream::clear_current_thread_streams()`
(a worker's last mlx action before it exits), not per-value lifetime
control.
- **Async Metal kernel failures bypass `Result` and abort the process** —
the rc/sentinel chain only catches synchronous errors. A `set_terminate`-style
recovery shim is not implementable (mlx-c exposes no hook); only diagnostics
are planned.
- **Each thread that calls into mlxrs allocates a GPU stream that lives
until process exit.** mlxrs is designed for a small, long-lived worker
pool — patterns that spawn a fresh OS thread per request will accumulate
streams without bound.
- **Operator overloads (`&a + &b`, `-&a`, etc.)** are gated behind the
`unstable-ops-overload` feature flag and **panic** on shape/dtype error.
Library authors must NEVER enable it transitively (Cargo features
unionize across the dep graph). End-user binaries may opt in for
prototyping. The fallible `a.add(&b)?` form is always available and is
the load-bearing API.
- **Per-model architectures** for the `lm` / `vlm` / `audio` / `embeddings`
features are added per-usecase rather than bulk-ported from the upstream
Python projects. These features ship the support surface (loaders, tokenizers,
pooling, generation loops, processors, audio I/O) — not the model
implementations.
#### License
`mlxrs` is under the terms of both the MIT license and the
Apache License (Version 2.0).
See [LICENSE-APACHE](LICENSE-APACHE), [LICENSE-MIT](LICENSE-MIT) for details.
Copyright (c) 2026 FinDIT Studio authors.
[Github-url]: https://github.com/findit-ai/mlxrs/
[CI-url]: https://github.com/findit-ai/mlxrs/actions/workflows/mlxrs.yml
[doc-url]: https://docs.rs/mlxrs
[crates-url]: https://crates.io/crates/mlxrs
[codecov-url]: https://app.codecov.io/gh/findit-ai/mlxrs/