AMD Vitis™ AI is an AMD development kit for AI inference on AMD hardware platforms. Machine learning inference is compute-intensive and requires high memory bandwidth to meet low-latency and high-throughput requirements.
The Vitis AI Optimizer provides the ability to optimize neural network models. Currently, the Vitis AI Optimizer includes only one tool called the pruner. The Vitis AI Optimizer removes redundant kernels in neural networks, reducing the overall computational cost for inference. Models pruned with the Vitis AI Optimizer can be quantized and deployed on AMD FPGA, SoC, or adaptive SoC devices.
The Vitis AI Optimizer supports TensorFlow and PyTorch. The corresponding tool names (_p_ denotes pruning) are listed in the following table.
|TensorFlow||vai_p_tensorflow (TF1.15), vai_p_tensorflow2 (TF2.x)|