lly-zero-one

Currently, the activation inputs and weight inputs are set together after compilation. For pre-compute pass in TVM, we need to know the weight inputs to do some optimization, such as...

More often than not, we need to "test" single TVM operator, which cannot be fused with other nodes so far. We expect the fusing pass still create one group for...

Thanks for contributing to TVM! Please refer to guideline https://docs.tvm.ai/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from [Reviewers](https://github.com/dmlc/tvm/blob/master/CONTRIBUTORS.md#reviewers).