Laya for runtimes & ports

laya.axera

AXERA-TECH

Exports and calibrates Laya models for AXERA NPU deployment

laya-serve

stiermid

Serves local Laya decision models through a Jev-compatible HTTP API

openzl-laya

madeye

Adds optional on-device Laya routing to OpenZL compression on Linux and macOS

laya-cuda

Alexw1111

Provides a lightweight CUDA inference library for Laya

laya-rs

Fanaperana

Reimplements Laya in Rust for zero-shot text classification with verified numerical parity

laya-candle

mannlohchab

Runs English Laya decision-model inference using the Candle framework

laya-research

igun997

Runs a grocery-market decision research bench with a Laya model behind its API

laya-go

brennanMKE

Pure-Go inference and a drop-in HTTP server run the Laya System 1 decision model

apex-decisioncore

AAH20

A pure-Python decision kernel combining state-space dynamics, action pruning, safety projection, and audit logging

laya-java

apscot

Runs Laya typed-decision models in Java and provides compatible endpoints and Spring Boot tooling

Provides quantized and full-precision Laya Multilingual GGUF files for llama.cpp

Packages Laya Multilingual as an F16 GGUF fixture for MeshLLM System One smoke tests

Provides F16 and quantized GGUF conversions of the multilingual Laya model for llama.cpp

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

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

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

Packages a calibrated Laya prompt-injection guardrail fine-tune for the Go Laya server

Provides an adaptive FP16 Core ML conversion of the Laya model for Apple silicon

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

Provides a multilingual non-autoregressive model for calibrated typed decisions over text

Exports Laya multilingual as an on-device Apple model for macOS and iPhone

Converts the Laya model to Core ML and ONNX for on-device use on iOS and Android

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

Provides fixed-shape Core ML artifacts converted from the 421M Laya typed-decisions checkpoint