You can add your own legalize strategy, refer to this PR: https://github.com/apache/tvm/pull/8222 But I’m not sure if you will really get speed up after padding. So you can also consider directly modifying the cuda strategy of your own conv2d_int8 so that it can be distributed to topi that does not require dp4a. https://github.com/apache/tvm/blob/5fa1c6dae0903f4dc31d39d42fcf582190ac1a68/python/tvm/relay/op/strategy/cuda.py#L119
--- [Visit Topic](https://discuss.tvm.apache.org/t/quantizatition-and-pruned-model/10308/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/d21b382f92bea40fe50f1d87568d18be945dc83b267b64b2dae5e4cbec1d3f29).
