A Heterogeneous Platform Deep Learning Compiler Framework from EdgeCortix

Automatic Schedule Exploration and Optimization Framework for Tensor Computations

Graphiler is a compiler stack built on top of DGL and TorchScript which compiles GNNs defined using user-defined functions (UDFs) into efficient execution plans.

The Tensor Algebra Compiler (taco) computes sparse tensor expressions on CPUs and GPUs

Puzzles for learning Triton

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

XLS: Accelerated HW Synthesis

📙 Source code for "BenchPress: A Deep Active Benchmark Generator", PACT 2022

Snapdragon Neural Processing Engine (SNPE) SDKThe Snapdragon Neural Processing Engine (SNPE) is a Qualcomm Snapdragon software accelerated runtime for the execution of deep neural networks. With SN…

Buda Compiler Backend for Tenstorrent devices

Tenstorrent TT-BUDA Repository

The Triton backend for TensorRT.

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

CMSIS-NN Library

AMD's Machine Intelligence Library

Open Source Specialized Computing Stack for Accelerating Deep Neural Networks.

nGraph has moved to OpenVINO

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Open, Modular, Deep Learning Accelerator

A polyhedral compiler for expressing fast and portable data parallel algorithms

Open Neural Network Compiler

Open deep learning compiler stack for Kendryte AI accelerators ✨

Enabling Flexible FPGA High-Level Synthesis of Tensorflow Deep Neural Networks

High-performance automatic differentiation of LLVM and MLIR.

Tenstorrent MLIR compiler

SparseTIR: Sparse Tensor Compiler for Deep Learning