mlx-snn: Spiking Neural Networks on Apple Silicon via MLX

• URL: http://arxiv.org/abs/2603.03529v1
• Date: Tue, 03 Mar 2026 21:25:36 GMT
• Title: mlx-snn: Spiking Neural Networks on Apple Silicon via MLX
• Abstract summary: We introduce mlx-snn, the first spiking neural network (SNN) library built on Apple's MLX framework.<n>mlx-snn provides six neuron models, four surrogate gradient functions, four spike encoding methods, and a complete backpropagation-through-time training pipeline.<n>mlx-snn is open-source under the MIT license and available on PyPI.
• Score: 1.1597621848542221
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce mlx-snn, the first spiking neural network (SNN) library built natively on Apple's MLX framework. As SNN research grows rapidly, all major libraries -- snnTorch, Norse, SpikingJelly, Lava -- target PyTorch or custom backends, leaving Apple Silicon users without a native option. mlx-snn provides six neuron models (LIF, IF, Izhikevich, Adaptive LIF, Synaptic, Alpha), four surrogate gradient functions, four spike encoding methods (including an EEG-specific encoder), and a complete backpropagation-through-time training pipeline. The library leverages MLX's unified memory architecture, lazy evaluation, and composable function transforms (mx.grad, mx.compile) to enable efficient SNN research on Apple Silicon hardware. We validate mlx-snn on MNIST digit classification across five hyperparameter configurations and three backends, achieving up to 97.28% accuracy with 2.0--2.5 times faster training and 3--10 times lower GPU memory than snnTorch on the same M3 Max hardware. mlx-snn is open-source under the MIT license and available on PyPI. https://github.com/D-ST-Sword/mlx-snn

Related papers

• BaseRT: Advancing Best-in-Class LLM Inference with Apple M5 Neural Accelerators [0.0]
  We show that BaseRT exploits the Metal inference for large language models on Apple Silicon.<n>On an Apple M5 Pro, BaseRT delivers up to $6.4times$ higher prompt-processing throughput than llama.<n>We show that the M5's tensor cores are the decisive lever for prompt processing on Apple Silicon.
  arXiv  Detail & Related papers  (2026-07-21T06:42:18Z)
• BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal [0.0]
  We present BaseRT, a native Metal runtime for large language models (LLMs) on Apple.<n>Report the highest inference throughput on this hardware to date.
  arXiv  Detail & Related papers  (2026-07-01T06:37:11Z)
• SNN-MLIR: An MLIR Dialect for Compiling Neuromorphic SNNs from NIR to Bare-Metal C [45.88028371034407]
  Spiking neural networks (SNNs) are increasingly trained in a wide range of frameworks each with its own model format.<n>Neuromorphic Intermediate Representation (NIR) addresses this fragmentation by providing a common, framework-independent format for exchanging trained SNN models.<n>Snn-mlir is an outof-tree MLIR dialect for SNNs together with a NIR-MLIR-C compilation bridge.
  arXiv  Detail & Related papers  (2026-06-08T08:47:48Z)
• mlx-vis: GPU-Accelerated Dimensionality Reduction and Visualization on Apple Silicon [5.943245848892104]
  mlx-vis is a Python library that implements six dimensionality reduction methods and a k-nearest neighbor graph entirely in MLX.<n>The library provides UMAP, t-SNE, PaCMAP, TriMap, DREAMS, CNE, and NNDescent, all executing on Metal GPU through a unified fit_transform interface.<n>On Fashion-MNIST with 70,000 points, all methods complete embedding in 2.1-3.8 seconds and render 800-frame animations in 1.4 seconds on an M3 Ultra.
  arXiv  Detail & Related papers  (2026-03-04T13:16:48Z)
• Native LLM and MLLM Inference at Scale on Apple Silicon [0.8122270502556375]
  We present vllm-mlx, a framework for efficient LLM and MLLM inference on Apple Silicon built native on MLX.<n>For text models, we achieve 21% to 87% higher throughput than llama- across models ranging from Qwen3-0.6B to Nemotron-30B.<n>For multimodal models, we introduce content-based caching that eliminates redundant vision encoding by identifying identical images through content hashing, regardless of input format.
  arXiv  Detail & Related papers  (2026-01-27T03:11:02Z)
• Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation [51.235583545740674]
  MaxLin is a robustness verifier for MaxPool-based CNNs with tight linear approximation. We evaluate MaxLin with open-sourced benchmarks, including LeNet and networks trained on the MNIST, CIFAR-10, and Tiny ImageNet datasets.
  arXiv  Detail & Related papers  (2024-06-02T10:33:04Z)
• Enabling High-Sparsity Foundational Llama Models with Efficient Pretraining and Deployment [56.44025052765861]
  Large language models (LLMs) have revolutionized Natural Language Processing (NLP), but their size creates computational bottlenecks. We introduce a novel approach to create accurate, sparse foundational versions of performant LLMs. We show a total speedup on CPUs for sparse-quantized LLaMA models of up to 8.6x.
  arXiv  Detail & Related papers  (2024-05-06T16:03:32Z)
• Recurrent Drafter for Fast Speculative Decoding in Large Language Models [18.342742904042673]
  We present Recurrent Drafter, an advanced speculative decoding approach.<n>It achieves state-of-the-art speedup for large language models (LLMs) inference.
  arXiv  Detail & Related papers  (2024-03-14T23:40:56Z)
• An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs [12.883586189626431]
  Transformer-based language models have become the standard approach for natural language processing tasks. Most existing neural network inference runtimes lack adequate support for structured sparsity. We propose an efficient sparse deep learning inference software stack for Transformer-based language models.
  arXiv  Detail & Related papers  (2023-06-28T23:55:51Z)
• Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis [51.0695452455959]
  We present a Non-parametric Network for 3D point cloud analysis, Point-NN, which consists of purely non-learnable components. Surprisingly, it performs well on various 3D tasks, requiring no parameters or training, and even surpasses existing fully trained models.
  arXiv  Detail & Related papers  (2023-03-14T17:59:02Z)
• Improved techniques for deterministic l2 robustness [63.34032156196848]
  Training convolutional neural networks (CNNs) with a strict 1-Lipschitz constraint under the $l_2$ norm is useful for adversarial robustness, interpretable gradients and stable training. We introduce a procedure to certify robustness of 1-Lipschitz CNNs by replacing the last linear layer with a 1-hidden layer. We significantly advance the state-of-the-art for standard and provable robust accuracies on CIFAR-10 and CIFAR-100.
  arXiv  Detail & Related papers  (2022-11-15T19:10:12Z)
• Compiling ONNX Neural Network Models Using MLIR [51.903932262028235]
  We present a preliminary report on our onnx-mlir compiler, which generates code for the inference of deep neural network models. Onnx-mlir relies on the Multi-Level Intermediate Representation (MLIR) infrastructure recently integrated in the LLVM project.
  arXiv  Detail & Related papers  (2020-08-19T05:28:08Z)
• Hybrid Models for Learning to Branch [81.93868699246214]
  We propose a new hybrid architecture for efficient branching on CPU machines. The proposed architecture combines the expressive power of GNNs with computationally inexpensive multi-layer perceptrons (MLP) for branching.
  arXiv  Detail & Related papers  (2020-06-26T21:03:45Z)
• Deep Learning in Memristive Nanowire Networks [0.0]
  A new hardware architecture, dubbed the MN3 (Memristive Nanowire Neural Network), was recently described as an efficient architecture for simulating very wide, sparse neural network layers. We show that the MN3 is capable of performing composition, gradient propagation, and weight updates, which together allow it to function as a deep neural network.
  arXiv  Detail & Related papers  (2020-03-03T20:11:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.