spectrometerHBH opened a new issue, #14335: URL: https://github.com/apache/tvm/issues/14335
https://github.com/apache/tvm/blob/unity/python/tvm/contrib/cutlass/gemm_operation.py#L372 I note here that if bias has 2 dims, the ldc will be N. If the bias is of shape (1, N), I suppose the ldc should still be 0? https://github.com/apache/tvm/blob/unity/tests/python/relax/test_codegen_cutlass.py#L398 It looks to me that only 1D bias cases are tested. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
