Auto-Tune with Templates and AutoTVM¶

AutoTVM offers a way to tune models and operators by providing a template schedule, and searcing the parameter space defined by the template. These how-tos demonstrate how to write template schedules and optimize them for a variety of different hardware platforms.

../../_images/sphx_glr_tune_conv2d_cuda_thumb.png

Tuning High Performance Convolution on NVIDIA GPUs¶

../../_images/sphx_glr_tune_relay_cuda_thumb.png

Auto-tuning a Convolutional Network for NVIDIA GPU¶

../../_images/sphx_glr_tune_relay_x86_thumb.png

Auto-tuning a Convolutional Network for x86 CPU¶

../../_images/sphx_glr_tune_relay_arm_thumb.png

Auto-tuning a Convolutional Network for ARM CPU¶

../../_images/sphx_glr_tune_relay_mobile_gpu_thumb.png

Auto-tuning a Convolutional Network for Mobile GPU¶

Gallery generated by Sphinx-Gallery