A community-driven and modular open source compiler for ML.

A high-throughput and memory-efficient inference and serving engine for LLMs

Backward compatible ML compute opset inspired by HLO/MHLO

AI Tensor Engine for ROCm

Composable Kernel: Performance Portable Programming Model for Machine Learning Tensor Operators

Code for running RFdiffusion

IREE's PyTorch Frontend, based on Torch Dynamo.

Python package built to ease deep learning on graph, on top of existing DL frameworks.

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at…

Firmware and controller app for DIY EMDR equipment (lightbar, buzzers and headphones)

ROCm Thrust - run Thrust dependent software on AMD GPUs

Header-only library of GPU-accelerated, concurrent data structures.

Reusable software components for ROCm developers

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

Representation and Reference Lowering of ONNX Models in MLIR Compiler Infrastructure

Open deep learning compiler stack for cpu, gpu and specialized accelerators

CI system for premerge-testing in LLVM project

"Multi-Level Intermediate Representation" Compiler Infrastructure

Dotfiles