Grouped-gemm

What's Changed
* Add `pyproject.toml` by eitanturok in https://github.com/tgale96/grouped_gemm/pull/16
* Use CUTLASS for both `trans_a` and `trans_b` on Ampere by dfyz in https://github.com/tgale96/grouped_gemm/pull/14
* bump torch, gg version by eitanturok in https://github.com/tgale96/grouped_gemm/pull/18

New Contributors
* eitanturok made their first contribution in https://github.com/tgale96/grouped_gemm/pull/16
* dfyz made their first contribution in https://github.com/tgale96/grouped_gemm/pull/14

**Full Changelog**: https://github.com/tgale96/grouped_gemm/compare/v0.1.4...v0.1.6

What's Changed
* Update manifest with cutlass by mvpatel2000 in https://github.com/tgale96/grouped_gemm/pull/10
* Capture .hpp files for pypi. by tgale96 in https://github.com/tgale96/grouped_gemm/pull/11
* ++version by tgale96 in https://github.com/tgale96/grouped_gemm/pull/12


**Full Changelog**: https://github.com/tgale96/grouped_gemm/compare/v0.1.2...v0.1.4

What's Changed
* Fix build when falling back to TORCH_CUDA_ARCH_LIST. by tgale96 in https://github.com/tgale96/grouped_gemm/pull/8
* Bump version by mvpatel2000 in https://github.com/tgale96/grouped_gemm/pull/9

New Contributors
* tgale96 made their first contribution in https://github.com/tgale96/grouped_gemm/pull/8

**Full Changelog**: https://github.com/tgale96/grouped_gemm/compare/v0.1.1...v0.1.2

What's Changed
* Update setup to be more flexible in cuda builds by mvpatel2000 in https://github.com/tgale96/grouped_gemm/pull/7

New Contributors
* mvpatel2000 made their first contribution in https://github.com/tgale96/grouped_gemm/pull/7

**Full Changelog**: https://github.com/tgale96/grouped_gemm/compare/v0.1...v0.1.1

Initial release.