ONNC 1.2.0 Released
We are excited to announce the v1.2.0 release of ONNC is now available! The new release of ONNC project includes major changes in NVDLA backend, improvement of framework support, and tools. ONNC can successfully compile 12 ONNX models and run inference on NVDLA virtual platform. (with nv_full hardware configuration)
For more information: https://github.com/ONNC/onnc/releases/
ONNC is an AI compiler specifically designed for proprietary deep-learning accelerators (DLAs) that support Open Neural Network Exchange (ONNX) models. ONNC leverages the ONNX IR design and optimizes neural network computation performance on various target runtime environments.
ONNC is the first open source compiler available for NVDLA-based hardware designs. Its NVDLA backend can compile a model into an executable NVDLA Loadable file. Integrating ONNC with the NVDLA software stack opens up opportunities for developers and researchers to explore the NVDLA-based inference design at the system level.