[Unity][BYOC] Support ND A and 2D B batched matmul for cublasLt

[masahi]

In our cublas BYOC where we use the newer cuBLASLt API, due to an API limitation ND x 2D or 2D x ND batched matmul have not been supported. But the former one can be easily supported by flattening all batch axes into the M axis and using the regular, non-batched GEMM.

@vinx13 @yelite @csullivan @sunggg

[tvm-bot]

Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment.

• cc @billishyahao, @quic-sanirudh _{See #10317 for details}

_{Generated by tvm-bot}