Clarify on why TRITON_MAX_TILE_NUMEL limits (2**17)

What is the reason for the max numel limit 2 **17 number? pytorch/test/test_sparse_csr.py at 44fae102774216bbba8df91f140bba54a30e5f62 · pytorch/pytorch · GitHub res_tri = bsr_softmax(bsr) res_coo = torch.sparse.softmax(coo, -1) self.assertEqual(res_tri, res_coo.to(input.dtype)) # Test long rows which exceed Triton's max numel limit set to 2 ** 17 input = tensor(b + (1, 150000)) bsr = input.to_sparse_bsr(1) self.assertEqual(i...