Dynamic support for split

[cehongwang]

Description

Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.

Fixes # (issue)

Type of change

Updated and added test cases for dynamic shape of split function
Add dynamic shape support tag in function decorator of converter

Checklist:

• My code follows the style guidelines of this project (You can use the linters)
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas and hacks
• I have made corresponding changes to the documentation
• I have added tests to verify my fix or my feature
• New and existing unit tests pass locally with my changes
• I have added the relevant labels to my PR in so that relevant reviewers are notified

[github-actions]

There are some changes that do not conform to Python style guidelines:

--- /home/runner/work/TensorRT/TensorRT/tests/py/dynamo/conversion/test_split_aten.py	2024-05-30 21:44:49.741396+00:00
+++ /home/runner/work/TensorRT/TensorRT/tests/py/dynamo/conversion/test_split_aten.py	2024-05-30 21:46:43.525899+00:00
@@ -135,11 +135,11 @@
            Input(
                dtype=torch.float32,
                min_shape=[1, 10, 1],
                opt_shape=[1, 10, 10],
                max_shape=[1, 10, 10],
-                name = "input",
+                name="input",
            ),
        ]
        self.run_test_with_dynamic_shape(
            TestModule(),
            input_specs,
@@ -163,18 +163,17 @@
            Input(
                dtype=torch.float32,
                min_shape=[1, 10, 10],
                opt_shape=[3, 10, 10],
                max_shape=[5, 10, 10],
-                name = "input",
+                name="input",
            ),
        ]
        self.run_test_with_dynamic_shape(
            TestModule(),
            input_specs,
        )
-

    @parameterized.expand(
        [
            ("select_chunk_dim", 6, 0),
        ]

[github-actions]

There are some changes that do not conform to Python style guidelines:

--- /home/runner/work/TensorRT/TensorRT/tests/py/dynamo/conversion/test_split_aten.py	2024-05-30 21:44:48.482825+00:00
+++ /home/runner/work/TensorRT/TensorRT/tests/py/dynamo/conversion/test_split_aten.py	2024-05-30 21:47:47.511710+00:00
@@ -135,11 +135,11 @@
            Input(
                dtype=torch.float32,
                min_shape=[1, 10, 1],
                opt_shape=[1, 10, 10],
                max_shape=[1, 10, 10],
-                name = "input",
+                name="input",
            ),
        ]
        self.run_test_with_dynamic_shape(
            TestModule(),
            input_specs,
@@ -163,18 +163,17 @@
            Input(
                dtype=torch.float32,
                min_shape=[1, 10, 10],
                opt_shape=[3, 10, 10],
                max_shape=[5, 10, 10],
-                name = "input",
+                name="input",
            ),
        ]
        self.run_test_with_dynamic_shape(
            TestModule(),
            input_specs,
        )
-

    @parameterized.expand(
        [
            ("select_chunk_dim", 6, 0),
        ]

[narendasan]

@cehongwang have you set up the precommit system, it can help you with the linting?

[peri044]

changes LGTM. pending CI