Fix the dtype values of zero-dimensional tensors in the premake functions

[voltjia]

pytest output:

============================= test session starts ==============================
platform linux -- Python 3.10.16, pytest-9.0.2, pluggy-1.6.0
rootdir: /home/huangjiacheng/ntops
configfile: pyproject.toml
plugins: anyio-4.12.1, cov-7.0.0
collected 676 items

tests/test_abs.py ........                                               [  1%]
tests/test_add.py ........                                               [  2%]
tests/test_addmm.py ..                                                   [  2%]
tests/test_bitwise_and.py ................                               [  5%]
tests/test_bitwise_not.py ................                               [  7%]
tests/test_bitwise_or.py ................                                [  9%]
tests/test_bmm.py ..                                                     [ 10%]
tests/test_clamp.py ........                                             [ 11%]
tests/test_cos.py ........                                               [ 12%]
tests/test_div.py .s..s..s..s..s..s..s..s.                               [ 15%]
tests/test_dropout.py ........                                           [ 17%]
tests/test_eq.py ........                                                [ 18%]
tests/test_exp.py ........                                               [ 19%]
tests/test_ge.py ........                                                [ 20%]
tests/test_gelu.py .s.s.s.s.s.s.s.s                                      [ 23%]
tests/test_gt.py ........                                                [ 24%]
tests/test_isinf.py ........                                             [ 25%]
tests/test_isnan.py ........                                             [ 26%]
tests/test_layer_norm.py ............................................... [ 33%]
.................................................                        [ 40%]
tests/test_le.py ........                                                [ 42%]
tests/test_lt.py ........                                                [ 43%]
tests/test_matmul.py ........                                            [ 44%]
tests/test_mm.py ..                                                      [ 44%]
tests/test_mul.py ........                                               [ 45%]
tests/test_ne.py ........                                                [ 47%]
tests/test_neg.py ........                                               [ 48%]
tests/test_pow.py ........                                               [ 49%]
tests/test_relu.py ................                                      [ 51%]
tests/test_rms_norm.py ................................................. [ 59%]
...............                                                          [ 61%]
tests/test_rotary_position_embedding.py ................................ [ 65%]
........................................................................ [ 76%]
........................                                                 [ 80%]
tests/test_rsqrt.py ........                                             [ 81%]
tests/test_scaled_dot_product_attention.py ............................. [ 85%]
.................................................                        [ 92%]
tests/test_sigmoid.py ........                                           [ 94%]
tests/test_silu.py ........                                              [ 95%]
tests/test_sin.py ........                                               [ 96%]
tests/test_softmax.py ........                                           [ 97%]
tests/test_sub.py ........                                               [ 98%]
tests/test_tanh.py ........                                              [100%]

=============================== warnings summary ===============================
tests/test_isinf.py: 12 warnings
  /home/huangjiacheng/.ninetoothed/e1f815a2d9d841f72f337e729448eb51cf763ebc8f4616cb50e283a7db760447.py:15: UserWarning: Logical operators 'and' and 'or' are deprecated for non-scalar tensors; please use '&' or '|' instead
    triton.language.store(ninetoothed_tensor_741_pointers + (ninetoothed_tensor_741_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_69 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_69)[::,]) * ninetoothed_ninetoothed_tensor_741_stride_0, pos_result or neg_result, mask=True & (ninetoothed_tensor_741_index_0 < (ninetoothed_ninetoothed_tensor_741_size_0 - (ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_69 - 1) - 1 + ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_69 - 1) // ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_69 + 1) & (triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_69)[::,] < ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_69) & (ninetoothed_tensor_741_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_69 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_69)[::,] < ninetoothed_ninetoothed_tensor_741_size_0) & (ninetoothed_tensor_741_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_69 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_69)[::,] < ninetoothed_ninetoothed_tensor_741_size_0))
  Enable tracemalloc to get traceback where the object was allocated.
  See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

tests/test_isinf.py: 12 warnings
  /home/huangjiacheng/.ninetoothed/08f00410bd95f52b1eb22854ceaf6b6e0fca5afb72babf7de0997209c7e20c9b.py:15: UserWarning: Logical operators 'and' and 'or' are deprecated for non-scalar tensors; please use '&' or '|' instead
    triton.language.store(ninetoothed_tensor_749_pointers + ((ninetoothed_tensor_749_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70)[::,]) // ninetoothed_ninetoothed_tensor_749_size_1 * ninetoothed_ninetoothed_tensor_749_stride_0 + (ninetoothed_tensor_749_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70)[::,]) % ninetoothed_ninetoothed_tensor_749_size_1 * ninetoothed_ninetoothed_tensor_749_stride_1), pos_result or neg_result, mask=True & (ninetoothed_tensor_749_index_0 < (ninetoothed_ninetoothed_tensor_749_size_0 * ninetoothed_ninetoothed_tensor_749_size_1 - (ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70 - 1) - 1 + ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70 - 1) // ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70 + 1) & (triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70)[::,] < ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70) & (ninetoothed_tensor_749_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70)[::,] < ninetoothed_ninetoothed_tensor_749_size_0 * ninetoothed_ninetoothed_tensor_749_size_1) & ((ninetoothed_tensor_749_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70)[::,]) // ninetoothed_ninetoothed_tensor_749_size_1 < ninetoothed_ninetoothed_tensor_749_size_0) & ((ninetoothed_tensor_749_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_70)[::,]) % ninetoothed_ninetoothed_tensor_749_size_1 < ninetoothed_ninetoothed_tensor_749_size_1))
  Enable tracemalloc to get traceback where the object was allocated.
  See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

tests/test_isinf.py: 12 warnings
  /home/huangjiacheng/.ninetoothed/186884898cdcf8c61ae23fe270f4c30e6e4085d93bc193e17245cbbb584055cb.py:15: UserWarning: Logical operators 'and' and 'or' are deprecated for non-scalar tensors; please use '&' or '|' instead
    triton.language.store(ninetoothed_tensor_757_pointers + ((ninetoothed_tensor_757_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71)[::,]) // (ninetoothed_ninetoothed_tensor_757_size_1 * ninetoothed_ninetoothed_tensor_757_size_2) * ninetoothed_ninetoothed_tensor_757_stride_0 + (ninetoothed_tensor_757_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71)[::,]) % (ninetoothed_ninetoothed_tensor_757_size_1 * ninetoothed_ninetoothed_tensor_757_size_2) // ninetoothed_ninetoothed_tensor_757_size_2 * ninetoothed_ninetoothed_tensor_757_stride_1 + (ninetoothed_tensor_757_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71)[::,]) % (ninetoothed_ninetoothed_tensor_757_size_1 * ninetoothed_ninetoothed_tensor_757_size_2) % ninetoothed_ninetoothed_tensor_757_size_2 * ninetoothed_ninetoothed_tensor_757_stride_2), pos_result or neg_result, mask=True & (ninetoothed_tensor_757_index_0 < (ninetoothed_ninetoothed_tensor_757_size_0 * ninetoothed_ninetoothed_tensor_757_size_1 * ninetoothed_ninetoothed_tensor_757_size_2 - (ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71 - 1) - 1 + ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71 - 1) // ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71 + 1) & (triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71)[::,] < ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71) & (ninetoothed_tensor_757_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71)[::,] < ninetoothed_ninetoothed_tensor_757_size_0 * ninetoothed_ninetoothed_tensor_757_size_1 * ninetoothed_ninetoothed_tensor_757_size_2) & ((ninetoothed_tensor_757_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71)[::,]) // (ninetoothed_ninetoothed_tensor_757_size_1 * ninetoothed_ninetoothed_tensor_757_size_2) < ninetoothed_ninetoothed_tensor_757_size_0) & ((ninetoothed_tensor_757_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71)[::,]) % (ninetoothed_ninetoothed_tensor_757_size_1 * ninetoothed_ninetoothed_tensor_757_size_2) // ninetoothed_ninetoothed_tensor_757_size_2 < ninetoothed_ninetoothed_tensor_757_size_1) & ((ninetoothed_tensor_757_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_71)[::,]) % (ninetoothed_ninetoothed_tensor_757_size_1 * ninetoothed_ninetoothed_tensor_757_size_2) % ninetoothed_ninetoothed_tensor_757_size_2 < ninetoothed_ninetoothed_tensor_757_size_2))
  Enable tracemalloc to get traceback where the object was allocated.
  See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

tests/test_isinf.py: 12 warnings
  /home/huangjiacheng/.ninetoothed/78f856f56af91b71d3158ad11c8487903d6a26469232b1ffbfd9aa9b03d42644.py:15: UserWarning: Logical operators 'and' and 'or' are deprecated for non-scalar tensors; please use '&' or '|' instead
    triton.language.store(ninetoothed_tensor_765_pointers + ((ninetoothed_tensor_765_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72)[::,]) // (ninetoothed_ninetoothed_tensor_765_size_1 * (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3)) * ninetoothed_ninetoothed_tensor_765_stride_0 + (ninetoothed_tensor_765_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72)[::,]) % (ninetoothed_ninetoothed_tensor_765_size_1 * (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3)) // (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3) * ninetoothed_ninetoothed_tensor_765_stride_1 + (ninetoothed_tensor_765_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72)[::,]) % (ninetoothed_ninetoothed_tensor_765_size_1 * (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3)) % (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3) // ninetoothed_ninetoothed_tensor_765_size_3 * ninetoothed_ninetoothed_tensor_765_stride_2 + (ninetoothed_tensor_765_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72)[::,]) % (ninetoothed_ninetoothed_tensor_765_size_1 * (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3)) % (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3) % ninetoothed_ninetoothed_tensor_765_size_3 * ninetoothed_ninetoothed_tensor_765_stride_3), pos_result or neg_result, mask=True & (ninetoothed_tensor_765_index_0 < (ninetoothed_ninetoothed_tensor_765_size_0 * ninetoothed_ninetoothed_tensor_765_size_1 * ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3 - (ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 - 1) - 1 + ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 - 1) // ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 + 1) & (triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72)[::,] < ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72) & (ninetoothed_tensor_765_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72)[::,] < ninetoothed_ninetoothed_tensor_765_size_0 * ninetoothed_ninetoothed_tensor_765_size_1 * ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3) & ((ninetoothed_tensor_765_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72)[::,]) // (ninetoothed_ninetoothed_tensor_765_size_1 * (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3)) < ninetoothed_ninetoothed_tensor_765_size_0) & ((ninetoothed_tensor_765_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72)[::,]) % (ninetoothed_ninetoothed_tensor_765_size_1 * (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3)) // (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3) < ninetoothed_ninetoothed_tensor_765_size_1) & ((ninetoothed_tensor_765_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72)[::,]) % (ninetoothed_ninetoothed_tensor_765_size_1 * (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3)) % (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3) // ninetoothed_ninetoothed_tensor_765_size_3 < ninetoothed_ninetoothed_tensor_765_size_2) & ((ninetoothed_tensor_765_index_0 * ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72 + triton.language.arange(0, ninetoothed_meta_prefix_ninetoothed_BLOCK_SIZE_72)[::,]) % (ninetoothed_ninetoothed_tensor_765_size_1 * (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3)) % (ninetoothed_ninetoothed_tensor_765_size_2 * ninetoothed_ninetoothed_tensor_765_size_3) % ninetoothed_ninetoothed_tensor_765_size_3 < ninetoothed_ninetoothed_tensor_765_size_3))
  Enable tracemalloc to get traceback where the object was allocated.
  See https://docs.pytest.org/en/stable/how-to/capture-warnings.html#resource-warnings for more info.

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
=========== 660 passed, 16 skipped, 48 warnings in 970.00s (0:16:09) ===========