onnxruntime/onnxruntime-qnn

QAI AppBuilder is designed to help developers easily execute models on WoS and Linux platforms. It encapsulates the Qualcomm® AI Runtime SDK APIs into a set of simplified interfaces for running models on the NPU/HTP.

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

Code sample showing how to run and benchmark models on Qualcomm's Window PCs

Inference RWKV v5, v6 and v7 with Qualcomm AI Engine Direct SDK

Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

Hexagon-MLIR is a compiler toolchain for compiling and executing AI kernels and models on Qualcomm Hexagon Neural Processing Units (NPUs).

QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX

High-efficiency floating-point neural network inference operators for mobile, server, and Web