Enable direct INT8/FP8 input in ONNX graph#354

gcunhase merged 1 commit intoNVIDIA:mainNVIDIA/TensorRT-Model-Optimizer:mainfrom

gcunhase:dev/gcunhasergio/add_direct_io_quantgcunhase/TensorRT-Model-Optimizer:dev/gcunhasergio/add_direct_io_quantCopy head branch name to clipboard