[sparse] add extra options to _cslt_spare_mm (#137427)

Summary:

Splitting this PR into two, one for the cuSPARSELt improvements, and one
for the inductor lowering.

This PR adds in the additional cuSPARSELt bindings into pytorch.

* `torch._cslt_sparse_mm_search` will be deprecated in a future PR,
  so a warning has been added

* Added a header file for cuSPARSELtOps.cpp

* max_id is now available in `torch.backends.cusparselt` via
  `torch.backends.cusparselt.get_max_alg_id()`

* fixed meta registrations for float8

Test Plan:

python test/test_sparse_semi_structured.py

Reviewers:

Subscribers:

Tasks:

Tags:

Pull Request resolved: https://github.com/pytorch/pytorch/pull/137427
Approved by: https://github.com/cpuhrsch, https://github.com/eqy

torch/sparse/_semi_structured_ops.py

@@ -103,6 +103,8 @@ def semi_sparse_detach(func, types, args, kwargs) -> torch.Tensor:
         packed_t=self.packed_t,
         meta_t=self.meta_t,
         compressed_swizzled_bitmask=self.compressed_swizzled_bitmask,
+        fuse_transpose_cusparselt=self.fuse_transpose_cusparselt,
+        alg_id_cusparselt=self.alg_id_cusparselt,
         requires_grad=False,
     )