The implementations for CUDA are defined in `topi/python/topi/cuda`. The strategy to select implementations for `conv2d` op is defined at [here](https://github.com/apache/incubator-tvm/blob/master/python/tvm/relay/op/strategy/cuda.py#L91-L198).
I don't understand your second question very well. Do you want to know how to write an AutoTVM template? --- [Visit Topic](https://discuss.tvm.ai/t/topi-winograd-convolution-performance-is-too-slow/6161/10) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/8df86f163eea0337918fa892abd0ccfb0e06c7a3c547bd49385e6246365eb220).
