Crate irithyll_core 

Core types and inference engine for irithyll streaming ML models.

irithyll-core provides loss functions, observation traits, a compact binary format, and branch-free traversal for deploying trained SGBT models on embedded targets (Cortex-M0+, 32KB flash).

Features

• Loss functions — squared, logistic, Huber, softmax, expectile, quantile
• Observation trait — zero-copy training interface with SampleRef
• 12-byte packed nodes — 5 nodes per 64-byte cache line
• Zero-copy EnsembleView — constructed from &[u8], no allocation after validation
• Branch-free traversal — cmov/csel child selection, no pipeline stalls
• #![no_std] — zero mandatory dependencies, runs on bare metal

Usage

use irithyll_core::{EnsembleView, FormatError};

// Load packed binary (e.g. from flash, file, or network)
let packed_bytes: &[u8] = &[/* exported via irithyll::export_embedded() */];
let view = EnsembleView::from_bytes(packed_bytes)?;
let prediction = view.predict(&[1.0f32, 2.0, 3.0]);

Re-exports

pub use error::FormatError;

pub use packed::EnsembleHeader;

pub use packed::PackedNode;

pub use packed::TreeEntry;

pub use packed_i16::PackedNodeI16;

pub use packed_i16::QuantizedEnsembleHeader;

pub use view::EnsembleView;

pub use view_i16::QuantizedEnsembleView;

pub use loss::Loss;

pub use loss::LossType;

pub use sample::Sample;alloc

pub use sample::Observation;

pub use sample::SampleRef;

pub use drift::DriftSignal;

pub use drift::DriftDetector;alloc

pub use drift::DriftDetectorState;alloc

pub use error::ConfigError;alloc

pub use error::IrithyllError;alloc

pub use error::Result;alloc

Modules

drift

Concept drift detection algorithms.

ensemblealloc

SGBT ensemble orchestrator – the core boosting loop.

error

Error types for irithyll-core.

featurealloc

Feature type declarations for streaming tree construction.

histogramalloc

Histogram-based feature binning for streaming tree construction.

learneralloc

Unified streaming learner trait for polymorphic model composition.

loss

Loss functions for gradient boosting.

math

Platform-agnostic f64 math operations.

packed

12-byte packed node format and ensemble binary layout.

packed_i16

8-byte quantized packed node format for integer-only inference.

quantize

f64 → f32 quantization utilities for packed export.

reservoiralloc

Reservoir computing primitives for streaming temporal models.

sample

Core observation trait and zero-copy sample types.

snnalloc

Spiking Neural Networks with online e-prop learning.

ssmalloc

State Space Models for streaming temporal feature extraction.

traverse

Branch-free tree traversal for packed nodes.

traverse_i16

Branch-free tree traversal for quantized i16 packed nodes.

treealloc

Streaming decision trees with Hoeffding-bound split decisions.

view

Zero-copy, zero-alloc inference view over a packed ensemble binary.

view_i16

Zero-copy, zero-alloc inference view over a quantized (int16) ensemble binary.