Laya for runtimes & ports

Converts Laya decision encoders into LiteRT graphs for Android GPU inference

Hosts ONNX-converted English Laya model weights in FP32, FP16, and INT8 formats

A GGUF conversion of Laya for inference with the laya-rust engine

Provides an int8 weight-only ONNX export of Laya for ONNX Runtime

Runs Laya English and typed-decision checkpoints on Android GPUs with LiteRT

An MXFP8 MLX quantization of Laya multilingual's encoder backbone for Apple Silicon

A Persian-optimized multilingual GGUF conversion of the Laya typed-decision model

Exports Laya as a Core ML model for local typed decisions through the Swev Swift package

Provides a Core AI conversion of multilingual Laya for typed decisions on Apple devices

Provides CPU-optimized, quantized ONNX checkpoints for multilingual Laya

Provides a quantized web build of Laya typed-decision models

Provides quantized ONNX checkpoints and a demo for running Laya in browsers

Provides an ONNX export of the Laya model

Converts Laya to a native MLX FP16 checkpoint for inference on Apple silicon

Provides multilingual Laya checkpoints for typed decisions over text and JSON states

Exports Laya checkpoints to ONNX for inference with ONNX Runtime

An int8 OpenVINO export of Laya for CPU inference

laya-jev

KonghaYao

Runs local Laya inference and exposes Jev-compatible HTTP endpoints

LayaKit

tahby

A Swift package for running Laya typed decisions on-device with Core ML

ultra_laya

roadius2

A fork of Laya adds multilingual decision routing and checkpoint selection

laya-go

lengoman

Provides Go types, routing, batching, and transports for using local Laya checkpoints

laya

xosi

Runs Laya typed-decision inference locally on Apple Silicon with MLX

laya-server

pambrose

Implements a Jev-compatible API server backed by local Laya checkpoints

localjev-mlx

rimusz

A self-hosted System One judgment service for Apple Silicon using laya-mlx