neurolib 0.1.0

NeuroLib: single entry point to the workspace - spike networks, layers, quantization, kernels, weight format and work with records; everything is enabled via features (analogue of the `burn` crate)
Documentation

NeuroLib

Spiking neural networks, quantized layers, fused kernels, a weight format and tools for neural recordings in Rust, built on Burn 0.22.

NeuroLib is created and maintained by Kostyanikov, lead of the Emphronic organization.

Crates

Module in neurolib Crate What it is
snn neo-snn Spiking layers on Burn: LIF/ALIF/Izhikevich/AdEx/Hodgkin-Huxley and more, surrogate gradients, STDP, spike attention, ANN to SNN conversion, structural plasticity, reservoir computing, telemetry
nn neo-nn Generic layers: quantized linear, MoE, transformer blocks, embeddings
quant neo-quantization GGUF Q4-Q8, K-quants, IQ series, NF4, ternary/TQ, INT1-INT8
synk neo-synk Fused CubeCL kernels: quantized GEMM, leaky scan, spike/surrogate operations
store neo-store .syn weight format: network graph (NIR compatible), checksums, mmap, sharding; synctl CLI
core, io, view, synapse neo-core, neo-io, neo-view, neo-synapse Recordings: time and buffers, formats (npy/npz, Zarr, NWB, SpikeGLX), viewing, spike metrics
- neo-gui Workbench application (GPUI): Explore, Curation and Training

neurolib is the single entry point: one dependency, everything else is enabled through features (the same idea as the burn crate).

[dependencies]
neurolib = { version = "0.1", features = ["snn", "wgpu"] }
burn = "0.22"

Feature groups: ml (default), signal, full. Backends: wgpu, cuda, rocm (plus fusion), flex for the CPU.

Quick start

Burn 0.22 has no backend type parameter: the backend is chosen by the Device.

use burn::tensor::{Device, Distribution, Tensor};
use neurolib::snn::neuron::{LeakyConfig, MultiStepLeaky};
use neurolib::snn::surrogate::ATan;

let device = Device::flex().autodiff(); // CPU with autodiff; Device::wgpu(..) for GPU
let layer = MultiStepLeaky::new(&LeakyConfig::new(0.9), &device);
let x: Tensor<3> = Tensor::random([8, 50, 128], Distribution::Normal(0.5, 1.0), &device);
let spikes = layer.forward(x, &ATan::default()); // [batch, time, features]

Kernels are reachable from the spiking module; the device picks the implementation (fused CubeCL kernel on wgpu/CUDA/ROCm, reference on the rest):

use neurolib::snn::leaky_scan_forward;
let u = leaky_scan_forward(input, mem0, beta);

License

Copyright (c) 2026 Kostyanikov (Emphronic).

Licensed under either of

at your option. The crates neo-core, neo-nn, neo-quantization, neo-snn and neo-synk are licensed under the MIT license only, see their Cargo.toml. neo-quantization contains portions derived from ggml / llama.cpp (MIT); see THIRD_PARTY_NOTICES.md and NOTICE.

Contribution

Unless you explicitly state otherwise, any contribution intentionally submitted for inclusion in NeuroLib by you shall be licensed under the same terms as the crate it is submitted to, without any additional terms or conditions.

Citation

See CITATION.cff.