Skip to content

BF16 is slower than fp16 of TensorRT 9.1 when running my R50 model on A800 GPU #6971

BF16 is slower than fp16 of TensorRT 9.1 when running my R50 model on A800 GPU

BF16 is slower than fp16 of TensorRT 9.1 when running my R50 model on A800 GPU #6971