Add nvmath segment_mm backend with per-batch grouped/looped control in UMA

[maxwelltsai]

This PR implements a driver of cuBLAS functional invocation needed by DGL SegmentMM operation using the nvmath-python library, which makes it possible to call cuBLAS functions directly from python without any compilation of C/C++ code needed. The original compilation path in the fairchem_cpp remains available.

The driver implements interfaces for calling cublasGemmEx() and cublasGemmGroupedBatchedEx(). Benchmarks have shown that each function has its own advantages, and so this PR implements a flag used_grouped_gemm to allow switching on a per-batch basis.

[meta-cla]

Hi @maxwelltsai!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!

[meta-cla]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

[github-actions]

This PR has been marked as stale because it has been open for 30 days with no activity.