Shypd.aiThe largest open index of AI toolsONNC is an open neural network compiler designed for deep learning accelerators. It provides a retargetable compilation framework for ONNX operators, transforming models into DLA-specific binary forms.
Trending
About
ONNC (Open Neural Network Compiler) is a retargetable compilation framework specifically engineered for proprietary deep learning accelerators. Its architecture facilitates easy porting to any Deep Learning Accelerator (DLA) design that supports ONNX (Open Neural Network Exchange) operators. ONNC ensures executability across diverse DLAs by converting ONNX models into DLA-specific binary forms, utilizing ONNX's intermediate representation (IR) design and efficient algorithms to minimize data movement overhead. Notably, ONNC is the first open-source compiler available for NVDLA-based hardware designs, capable of compiling models into executable NVDLA Loadable files. Integrating ONNC with the NVDLA software stack empowers developers and researchers to explore NVDLA-based inference design at a system level.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
