AI SoftwareWeb linkPublished
ONNX Runtime — Cross-Platform Edge AI and NPU Inference
Production inference engine that targets NPUs, GPUs and CPUs across platforms via hardware execution providers.
About this resource
ONNX Runtime runs the same model across cloud and edge with acceleration for NPUs (Qualcomm QNN, AMD XDNA, Intel, NXP) through execution providers — the de-facto abstraction layer for edge AI deployment. Source: https://onnxruntime.ai
NPUedgeinferenceframework