Laya for runtimes & ports

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

Exports multilingual Laya as a portable Core ML bundle for Apple devices

Provides quantized ONNX exports of English and multilingual Laya checkpoints

Exports Laya to ONNX for use with Node.js or ONNX Runtime

laymbda

HQarroum

Runs the Laya decision model as a CPU-only AWS Lambda function with SnapStart

vgi-laya

lmangani

Runs local Laya inference in DuckDB to filter, classify, and score rows

laya-onnx

MstyAI

Runs Laya decision models locally with ONNX Runtime through a Go library and CLI

laya-zig

li-ming1

Runs the Laya decision model on CPU with a dependency-free Zig runtime

deqio

ILuce

Serves multiple typed-decision models, including Laya, through a local API and browser UI

LibLayaX

DaragonTech

An in-process C API library runs the Laya typed-decision model locally across desktop platforms

Converts Laya decision encoders into LiteRT graphs for Android GPU inference

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

Packages Laya checkpoints for deployment on AXERA AX650 and AX8850 NPUs

Exports multilingual Laya to ONNX for native and browser WebGPU inference

An int8 OpenVINO export of Laya for CPU inference

laya.cpp

shpati

Ports the Laya model to C and C++ for CPU inference on Linux and Windows

Bud-Decision-Engine

BudEcosystem

Desktop app and local server for Laya and other Jev-like decision models

vegaml

NandhaKishorM

Produces calibrated typed decisions from frozen language models with conformal sets and abstention

Provides 4-bit weight-only ONNX quantizations of Laya’s multilingual decision model

chunklaya

myxamediyar

Chunks long documents and uses Laya for typed-decision lookup across inputs up to one million tokens

laya-onnx

gqgs

Exports the Laya model to quantized ONNX for browser inference

laya-candle

b0xtch

Runs Laya safetensors natively in Rust with Candle and CPU, Metal, or CUDA backends

laya-web

r4ai

Runs Laya typed-decision models in browsers and Node.js using ONNX Runtime Web

docker-laya

chneau

Serves Laya typed-decision predictions through an authenticated, multi-checkpoint FastAPI service