Mlir Python Packages

ncnn

ncnn is a high-performance neural network inference framework optimized for the mobile platform

pnnx

ncnn is a high-performance neural network inference framework optimized for the mobile platform

iree-base-compiler

A retargetable MLIR-based machine learning compiler and runtime toolkit.

iree-base-runtime

A retargetable MLIR-based machine learning compiler and runtime toolkit.

iree-turbine

IREE's PyTorch Frontend, based on Torch Dynamo.

pennylane-catalyst

A JIT compiler for hybrid quantum programs in PennyLane

pymlir

Python interface for MLIR - the Multi-Level Intermediate Representation

iree-tools-tflite

A retargetable MLIR-based machine learning compiler and runtime toolkit.

iree-tools-tf

A retargetable MLIR-based machine learning compiler and runtime toolkit.

heir-py

A compiler for homomorphic encryption

concrete-python

Concrete: TFHE Compiler that converts python programs into FHE equivalent

iree-runtime

A retargetable MLIR-based machine learning compiler and runtime toolkit.

docc-compiler

Daisytuner Optimizing Compiler Collection (docc)

belfort-heir

A compiler for homomorphic encryption

docc-ai

Daisytuner Optimizing Compiler Collection (docc)

iree-runtime-instrumented

IREE Python Runtime Components

torch-quant

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

iree-tools-xla

IREE XLA Compiler Tools

teraxlang

A language and compiler for custom Deep Learning operations

sheaf-lang

A functional language for machine learning. Inspired by Clojure, compiled to GPUs.

heir-play

A cell magic enabling one to run HEIR pipelines in Jupyter notebooks.

polyinfer

Unified deployment pipeline

widip

A higher-order computing system

compilerinterface

Library to interface Compilers and ML models for ML-Enabled Compiler Optimizations