Skip to content

fix(aten::instance_norm): Handle optional inputs in instance norm con… #3367

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Jan 30, 2025

Conversation

narendasan
Copy link
Collaborator

…verter

Description

Fixes some of the issues in NGC container

Fixes # (issue)

Type of change

Please delete options that are not relevant and/or add your own.

  • Bug fix (non-breaking change which fixes an issue)

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

@narendasan narendasan requested a review from peri044 January 29, 2025 19:36
@github-actions github-actions bot added component: tests Issues re: Tests component: conversion Issues re: Conversion stage component: core Issues re: The core compiler component: converters Issues re: Specific op converters labels Jan 29, 2025
@github-actions github-actions bot requested a review from zewenli98 January 29, 2025 19:36
Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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

diff --git a/home/runner/work/TensorRT/TensorRT/core/conversion/converters/impl/batch_norm.cpp b/tmp/changes.txt
index 267b586..c8ec197 100644
--- a/home/runner/work/TensorRT/TensorRT/core/conversion/converters/impl/batch_norm.cpp
+++ b/tmp/changes.txt
@@ -134,13 +134,12 @@ auto batch_norm_registrations TORCHTRT_UNUSED =

              auto eps = static_cast<float>(args[7].unwrapToDouble(1e-5f));

-
              auto scales = at::ones(shape[1], options);
              if (!args[1].IValue()->isNone()) {
                scales = args[1].unwrapToTensor(at::ones(shape[1], options)).cpu().contiguous();
              }
              auto bias = at::zeros(shape[1], options);
-              if (!args[2].IValue()->isNone()){
+              if (!args[2].IValue()->isNone()) {
                bias = args[2].unwrapToTensor(at::zeros(shape[1], options)).cpu().contiguous();
              }
              // track_running_stats=True
@@ -170,7 +169,7 @@ auto batch_norm_registrations TORCHTRT_UNUSED =
                    so for some functionalities, users need to install correct \
                    cuDNN version by themselves. Please see our support matrix \
                    here: https://docs.nvidia.com/deeplearning/tensorrt/support-matrix/index.html.");
-                //return false;
+                // return false;
              }

              const int relu = 0;
ERROR: Some files do not conform to style guidelines

Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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

diff --git a/home/runner/work/TensorRT/TensorRT/core/conversion/converters/impl/batch_norm.cpp b/tmp/changes.txt
index 267b586..c8ec197 100644
--- a/home/runner/work/TensorRT/TensorRT/core/conversion/converters/impl/batch_norm.cpp
+++ b/tmp/changes.txt
@@ -134,13 +134,12 @@ auto batch_norm_registrations TORCHTRT_UNUSED =

              auto eps = static_cast<float>(args[7].unwrapToDouble(1e-5f));

-
              auto scales = at::ones(shape[1], options);
              if (!args[1].IValue()->isNone()) {
                scales = args[1].unwrapToTensor(at::ones(shape[1], options)).cpu().contiguous();
              }
              auto bias = at::zeros(shape[1], options);
-              if (!args[2].IValue()->isNone()){
+              if (!args[2].IValue()->isNone()) {
                bias = args[2].unwrapToTensor(at::zeros(shape[1], options)).cpu().contiguous();
              }
              // track_running_stats=True
@@ -170,7 +169,7 @@ auto batch_norm_registrations TORCHTRT_UNUSED =
                    so for some functionalities, users need to install correct \
                    cuDNN version by themselves. Please see our support matrix \
                    here: https://docs.nvidia.com/deeplearning/tensorrt/support-matrix/index.html.");
-                //return false;
+                // return false;
              }

              const int relu = 0;
ERROR: Some files do not conform to style guidelines

Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/0e30a6276601af7e5fc4d5166e2e3d37/torch_compile_advanced_usage.py	2025-01-29 19:36:39.024741+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/0e30a6276601af7e5fc4d5166e2e3d37/torch_compile_advanced_usage.py	2025-01-29 19:37:06.269420+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_advanced_usage:

Torch Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/2a9ac10f2667047a7f398d1593b7ca33/torch_export_gpt2.py	2025-01-29 19:36:39.024741+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/2a9ac10f2667047a7f398d1593b7ca33/torch_export_gpt2.py	2025-01-29 19:37:06.277587+00:00
@@ -2,11 +2,12 @@
.. _torch_export_gpt2:

Compiling GPT2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 19:36:39.025741+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 19:37:06.325770+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_resnet:

Compiling ResNet using the Torch-TensorRT Dyanmo Frontend
==========================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/3d4d74f6636d986f33167154f6553961/torch_export_cudagraphs.py	2025-01-29 19:36:39.024741+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/3d4d74f6636d986f33167154f6553961/torch_export_cudagraphs.py	2025-01-29 19:37:06.343057+00:00
@@ -2,11 +2,12 @@
.. _torch_export_cudagraphs:

Torch Export with Cudagraphs
======================================================

-This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well."""
+This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/7b7004dc2ea6f839be532665e16e0426/torch_export_llama2.py	2025-01-29 19:36:39.027741+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/7b7004dc2ea6f839be532665e16e0426/torch_export_llama2.py	2025-01-29 19:37:06.370229+00:00
@@ -2,11 +2,12 @@
.. _torch_export_llama2:

Compiling Llama2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 19:36:39.029741+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 19:37:06.450615+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_advanced_usage:

Dynamo Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/dfa60e8f9850fd7761f3e7da81304d32/torch_compile_transformers_example.py	2025-01-29 19:36:39.029741+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/dfa60e8f9850fd7761f3e7da81304d32/torch_compile_transformers_example.py	2025-01-29 19:37:06.454081+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling BERT using the `torch.compile` backend
==============================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/d6e1bb6ec5f884994554d9d12e37a0f6/torch_compile_resnet_example.py	2025-01-29 19:36:39.029741+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/d6e1bb6ec5f884994554d9d12e37a0f6/torch_compile_resnet_example.py	2025-01-29 19:37:06.465458+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_resnet:

Compiling ResNet with dynamic shapes using the `torch.compile` backend
==========================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 19:36:39.029741+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 19:37:06.500315+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling a Transformer using torch.compile and TensorRT
==============================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 19:36:39.494740+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 19:37:06.512245+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_resnet:

Compiling ResNet using the Torch-TensorRT Dyanmo Frontend
==========================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 19:36:39.494740+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 19:37:06.526084+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_advanced_usage:

Dynamo Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 19:36:39.494740+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 19:37:06.546110+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling a Transformer using torch.compile and TensorRT
==============================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_advanced_usage.py	2025-01-29 19:36:39.525740+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_advanced_usage.py	2025-01-29 19:37:06.723737+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_advanced_usage:

Torch Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_resnet_example.py	2025-01-29 19:36:39.525740+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_resnet_example.py	2025-01-29 19:37:06.741589+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_resnet:

Compiling ResNet with dynamic shapes using the `torch.compile` backend
==========================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_transformers_example.py	2025-01-29 19:36:39.525740+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_transformers_example.py	2025-01-29 19:37:06.751327+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling BERT using the `torch.compile` backend
==============================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_cudagraphs.py	2025-01-29 19:36:39.525740+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_cudagraphs.py	2025-01-29 19:37:06.771073+00:00
@@ -2,11 +2,12 @@
.. _torch_export_cudagraphs:

Torch Export with Cudagraphs
======================================================

-This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well."""
+This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_gpt2.py	2025-01-29 19:36:39.525740+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_gpt2.py	2025-01-29 19:37:06.771929+00:00
@@ -2,11 +2,12 @@
.. _torch_export_gpt2:

Compiling GPT2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_llama2.py	2025-01-29 19:36:39.525740+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_llama2.py	2025-01-29 19:37:06.785828+00:00
@@ -2,11 +2,12 @@
.. _torch_export_llama2:

Compiling Llama2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_Input.py	2025-01-29 19:36:39.534740+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_Input.py	2025-01-29 19:37:07.312686+00:00
@@ -259,11 +259,11 @@
        else:
            return False

    @staticmethod
    def _parse_tensor_domain(
-        domain: Optional[Tuple[float, float]]
+        domain: Optional[Tuple[float, float]],
    ) -> Tuple[float, float]:
        """
        Produce a tuple of integers which specifies a tensor domain in the interval format: [lo, hi)

        Args:
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/_TRTBuilderMonitor.py	2025-01-29 19:36:39.536740+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/_TRTBuilderMonitor.py	2025-01-29 19:37:07.568443+00:00
@@ -51,17 +51,17 @@

    def _redraw(self, *, blank_lines: int = 0) -> None:
        if self._render:

            def clear_line() -> None:
-                print("\x1B[2K", end="")
+                print("\x1b[2K", end="")

            def move_to_start_of_line() -> None:
-                print("\x1B[0G", end="")
+                print("\x1b[0G", end="")

            def move_cursor_up(lines: int) -> None:
-                print("\x1B[{}A".format(lines), end="")
+                print("\x1b[{}A".format(lines), end="")

            def progress_bar(steps: int, num_steps: int) -> str:
                INNER_WIDTH = 10
                completed_bar_chars = int(INNER_WIDTH * steps / float(num_steps))
                return "[{}{}]".format(
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_enums.py	2025-01-29 19:36:39.534740+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_enums.py	2025-01-29 19:37:07.817569+00:00
@@ -1198,11 +1198,11 @@
            "Provided unsupported source type for EngineCapability conversion"
        )

    @classmethod
    def try_from(
-        c: Union[trt.EngineCapability, EngineCapability]
+        c: Union[trt.EngineCapability, EngineCapability],
    ) -> Optional[EngineCapability]:
        """Create a Torch-TensorRT engine capability enum from a TensorRT engine capability enum.

        Takes a device type enum from tensorrt and create a ``torch_tensorrt.EngineCapability``.
        If the source is not supported or the engine capability level is not supported in Torch-TensorRT,
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/impl/activation/ops.py	2025-01-29 19:36:39.537740+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/impl/activation/ops.py	2025-01-29 19:37:08.001864+00:00
@@ -245,11 +245,11 @@
    beta: float,
) -> TRTTensor:
    operation_type = trt.ActivationType.HARD_SIGMOID

    def hard_sigmoid_dyn_range_fn(
-        dyn_range: Tuple[float, float]
+        dyn_range: Tuple[float, float],
    ) -> Tuple[float, float]:
        def hard_sigmoid_fn(x: float) -> float:
            return max(0, min(1, alpha * x + beta))

        return hard_sigmoid_fn(dyn_range[0]), hard_sigmoid_fn(dyn_range[1])
@@ -308,11 +308,11 @@
    alpha: float,
) -> TRTTensor:
    operation_type = trt.ActivationType.THRESHOLDED_RELU

    def thresholded_relu_dyn_range_fn(
-        dyn_range: Tuple[float, float]
+        dyn_range: Tuple[float, float],
    ) -> Tuple[float, float]:
        def thresholded_relu_fn(x: float) -> float:
            return x if x > alpha else 0

        return thresholded_relu_fn(dyn_range[0]), thresholded_relu_fn(dyn_range[1])
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/utils.py	2025-01-29 19:36:39.541740+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/utils.py	2025-01-29 19:37:09.732455+00:00
@@ -463,11 +463,11 @@
    else:
        return torch.device(device)


def to_torch_tensorrt_device(
-    device: Optional[Union[Device, torch.device, str]]
+    device: Optional[Union[Device, torch.device, str]],
) -> Device:
    """Cast a device-type to torch_tensorrt.Device

    Returns the corresponding torch_tensorrt.Device
    """
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/test/converters/acc_op/test_where.py	2025-01-29 19:36:39.546740+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/test/converters/acc_op/test_where.py	2025-01-29 19:37:10.459191+00:00
@@ -99,11 +99,11 @@
                self.y = torch.ones(y_shape)

            def forward(self, condition):
                return torch.where(condition, self.x, self.y)

-        inputs = [(torch.randn(condition_shape) > 0)]
+        inputs = [torch.randn(condition_shape) > 0]
        self.run_test(
            Where(x_shape, y_shape),
            inputs,
            expected_ops={acc_ops.where},
            test_implicit_batch_dim=False,
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/tracer/acc_tracer/acc_tracer.py	2025-01-29 19:36:39.550740+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/tracer/acc_tracer/acc_tracer.py	2025-01-29 19:37:11.750889+00:00
@@ -515,11 +515,11 @@
    dim0 = cast(int, transpose_node.args[1])
    dim1 = cast(int, transpose_node.args[2])
    changed = False

    def _calculate_dim(
-        transpose_dim: Union[torch.fx.Node, int]
+        transpose_dim: Union[torch.fx.Node, int],
    ) -> Union[torch.fx.Node, int]:
        nonlocal transpose_input_node
        nonlocal changed
        if isinstance(transpose_dim, torch.fx.Node):
            # Transpose dim is sub node

Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/0e30a6276601af7e5fc4d5166e2e3d37/torch_compile_advanced_usage.py	2025-01-29 19:36:39.564405+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/0e30a6276601af7e5fc4d5166e2e3d37/torch_compile_advanced_usage.py	2025-01-29 19:37:10.655493+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_advanced_usage:

Torch Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/2a9ac10f2667047a7f398d1593b7ca33/torch_export_gpt2.py	2025-01-29 19:36:39.564405+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/2a9ac10f2667047a7f398d1593b7ca33/torch_export_gpt2.py	2025-01-29 19:37:10.668049+00:00
@@ -2,11 +2,12 @@
.. _torch_export_gpt2:

Compiling GPT2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 19:36:39.565405+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 19:37:10.712228+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_resnet:

Compiling ResNet using the Torch-TensorRT Dyanmo Frontend
==========================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/3d4d74f6636d986f33167154f6553961/torch_export_cudagraphs.py	2025-01-29 19:36:39.565405+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/3d4d74f6636d986f33167154f6553961/torch_export_cudagraphs.py	2025-01-29 19:37:10.722646+00:00
@@ -2,11 +2,12 @@
.. _torch_export_cudagraphs:

Torch Export with Cudagraphs
======================================================

-This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well."""
+This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/7b7004dc2ea6f839be532665e16e0426/torch_export_llama2.py	2025-01-29 19:36:39.569405+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/7b7004dc2ea6f839be532665e16e0426/torch_export_llama2.py	2025-01-29 19:37:10.765635+00:00
@@ -2,11 +2,12 @@
.. _torch_export_llama2:

Compiling Llama2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 19:36:39.572405+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 19:37:10.833730+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_advanced_usage:

Dynamo Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/dfa60e8f9850fd7761f3e7da81304d32/torch_compile_transformers_example.py	2025-01-29 19:36:39.572405+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/dfa60e8f9850fd7761f3e7da81304d32/torch_compile_transformers_example.py	2025-01-29 19:37:10.836616+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling BERT using the `torch.compile` backend
==============================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/d6e1bb6ec5f884994554d9d12e37a0f6/torch_compile_resnet_example.py	2025-01-29 19:36:39.572405+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/d6e1bb6ec5f884994554d9d12e37a0f6/torch_compile_resnet_example.py	2025-01-29 19:37:10.844011+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_resnet:

Compiling ResNet with dynamic shapes using the `torch.compile` backend
==========================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 19:36:39.572405+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 19:37:10.881087+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling a Transformer using torch.compile and TensorRT
==============================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 19:36:40.034409+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 19:37:10.895013+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_resnet:

Compiling ResNet using the Torch-TensorRT Dyanmo Frontend
==========================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 19:36:40.035409+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 19:37:10.908179+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_advanced_usage:

Dynamo Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 19:36:40.035409+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 19:37:10.927471+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling a Transformer using torch.compile and TensorRT
==============================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_advanced_usage.py	2025-01-29 19:36:40.065409+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_advanced_usage.py	2025-01-29 19:37:11.073668+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_advanced_usage:

Torch Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_resnet_example.py	2025-01-29 19:36:40.065409+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_resnet_example.py	2025-01-29 19:37:11.136215+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_resnet:

Compiling ResNet with dynamic shapes using the `torch.compile` backend
==========================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_transformers_example.py	2025-01-29 19:36:40.066409+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_transformers_example.py	2025-01-29 19:37:11.144777+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling BERT using the `torch.compile` backend
==============================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_cudagraphs.py	2025-01-29 19:36:40.066409+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_cudagraphs.py	2025-01-29 19:37:11.152833+00:00
@@ -2,11 +2,12 @@
.. _torch_export_cudagraphs:

Torch Export with Cudagraphs
======================================================

-This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well."""
+This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_gpt2.py	2025-01-29 19:36:40.066409+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_gpt2.py	2025-01-29 19:37:11.158252+00:00
@@ -2,11 +2,12 @@
.. _torch_export_gpt2:

Compiling GPT2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_llama2.py	2025-01-29 19:36:40.066409+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_llama2.py	2025-01-29 19:37:11.186821+00:00
@@ -2,11 +2,12 @@
.. _torch_export_llama2:

Compiling Llama2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_Input.py	2025-01-29 19:36:40.075409+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_Input.py	2025-01-29 19:37:11.692124+00:00
@@ -259,11 +259,11 @@
        else:
            return False

    @staticmethod
    def _parse_tensor_domain(
-        domain: Optional[Tuple[float, float]]
+        domain: Optional[Tuple[float, float]],
    ) -> Tuple[float, float]:
        """
        Produce a tuple of integers which specifies a tensor domain in the interval format: [lo, hi)

        Args:
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/_TRTBuilderMonitor.py	2025-01-29 19:36:40.077410+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/_TRTBuilderMonitor.py	2025-01-29 19:37:11.960189+00:00
@@ -51,17 +51,17 @@

    def _redraw(self, *, blank_lines: int = 0) -> None:
        if self._render:

            def clear_line() -> None:
-                print("\x1B[2K", end="")
+                print("\x1b[2K", end="")

            def move_to_start_of_line() -> None:
-                print("\x1B[0G", end="")
+                print("\x1b[0G", end="")

            def move_cursor_up(lines: int) -> None:
-                print("\x1B[{}A".format(lines), end="")
+                print("\x1b[{}A".format(lines), end="")

            def progress_bar(steps: int, num_steps: int) -> str:
                INNER_WIDTH = 10
                completed_bar_chars = int(INNER_WIDTH * steps / float(num_steps))
                return "[{}{}]".format(
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_enums.py	2025-01-29 19:36:40.075409+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_enums.py	2025-01-29 19:37:12.174794+00:00
@@ -1198,11 +1198,11 @@
            "Provided unsupported source type for EngineCapability conversion"
        )

    @classmethod
    def try_from(
-        c: Union[trt.EngineCapability, EngineCapability]
+        c: Union[trt.EngineCapability, EngineCapability],
    ) -> Optional[EngineCapability]:
        """Create a Torch-TensorRT engine capability enum from a TensorRT engine capability enum.

        Takes a device type enum from tensorrt and create a ``torch_tensorrt.EngineCapability``.
        If the source is not supported or the engine capability level is not supported in Torch-TensorRT,
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/impl/activation/ops.py	2025-01-29 19:36:40.078409+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/impl/activation/ops.py	2025-01-29 19:37:12.385590+00:00
@@ -245,11 +245,11 @@
    beta: float,
) -> TRTTensor:
    operation_type = trt.ActivationType.HARD_SIGMOID

    def hard_sigmoid_dyn_range_fn(
-        dyn_range: Tuple[float, float]
+        dyn_range: Tuple[float, float],
    ) -> Tuple[float, float]:
        def hard_sigmoid_fn(x: float) -> float:
            return max(0, min(1, alpha * x + beta))

        return hard_sigmoid_fn(dyn_range[0]), hard_sigmoid_fn(dyn_range[1])
@@ -308,11 +308,11 @@
    alpha: float,
) -> TRTTensor:
    operation_type = trt.ActivationType.THRESHOLDED_RELU

    def thresholded_relu_dyn_range_fn(
-        dyn_range: Tuple[float, float]
+        dyn_range: Tuple[float, float],
    ) -> Tuple[float, float]:
        def thresholded_relu_fn(x: float) -> float:
            return x if x > alpha else 0

        return thresholded_relu_fn(dyn_range[0]), thresholded_relu_fn(dyn_range[1])
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/utils.py	2025-01-29 19:36:40.082410+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/utils.py	2025-01-29 19:37:13.840024+00:00
@@ -463,11 +463,11 @@
    else:
        return torch.device(device)


def to_torch_tensorrt_device(
-    device: Optional[Union[Device, torch.device, str]]
+    device: Optional[Union[Device, torch.device, str]],
) -> Device:
    """Cast a device-type to torch_tensorrt.Device

    Returns the corresponding torch_tensorrt.Device
    """
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/test/converters/acc_op/test_where.py	2025-01-29 19:36:40.087409+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/test/converters/acc_op/test_where.py	2025-01-29 19:37:14.801177+00:00
@@ -99,11 +99,11 @@
                self.y = torch.ones(y_shape)

            def forward(self, condition):
                return torch.where(condition, self.x, self.y)

-        inputs = [(torch.randn(condition_shape) > 0)]
+        inputs = [torch.randn(condition_shape) > 0]
        self.run_test(
            Where(x_shape, y_shape),
            inputs,
            expected_ops={acc_ops.where},
            test_implicit_batch_dim=False,
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/tracer/acc_tracer/acc_tracer.py	2025-01-29 19:36:40.091410+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/tracer/acc_tracer/acc_tracer.py	2025-01-29 19:37:16.009485+00:00
@@ -515,11 +515,11 @@
    dim0 = cast(int, transpose_node.args[1])
    dim1 = cast(int, transpose_node.args[2])
    changed = False

    def _calculate_dim(
-        transpose_dim: Union[torch.fx.Node, int]
+        transpose_dim: Union[torch.fx.Node, int],
    ) -> Union[torch.fx.Node, int]:
        nonlocal transpose_input_node
        nonlocal changed
        if isinstance(transpose_dim, torch.fx.Node):
            # Transpose dim is sub node

Copy link
Collaborator

@peri044 peri044 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@narendasan narendasan mentioned this pull request Jan 29, 2025
7 tasks
Copy link
Collaborator

@zewenli98 zewenli98 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Need to lint. others LGTM

Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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

diff --git a/home/runner/work/TensorRT/TensorRT/core/conversion/converters/impl/batch_norm.cpp b/tmp/changes.txt
index 267b586..c8ec197 100644
--- a/home/runner/work/TensorRT/TensorRT/core/conversion/converters/impl/batch_norm.cpp
+++ b/tmp/changes.txt
@@ -134,13 +134,12 @@ auto batch_norm_registrations TORCHTRT_UNUSED =

              auto eps = static_cast<float>(args[7].unwrapToDouble(1e-5f));

-
              auto scales = at::ones(shape[1], options);
              if (!args[1].IValue()->isNone()) {
                scales = args[1].unwrapToTensor(at::ones(shape[1], options)).cpu().contiguous();
              }
              auto bias = at::zeros(shape[1], options);
-              if (!args[2].IValue()->isNone()){
+              if (!args[2].IValue()->isNone()) {
                bias = args[2].unwrapToTensor(at::zeros(shape[1], options)).cpu().contiguous();
              }
              // track_running_stats=True
@@ -170,7 +169,7 @@ auto batch_norm_registrations TORCHTRT_UNUSED =
                    so for some functionalities, users need to install correct \
                    cuDNN version by themselves. Please see our support matrix \
                    here: https://docs.nvidia.com/deeplearning/tensorrt/support-matrix/index.html.");
-                //return false;
+                // return false;
              }

              const int relu = 0;
ERROR: Some files do not conform to style guidelines

Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/0e30a6276601af7e5fc4d5166e2e3d37/torch_compile_advanced_usage.py	2025-01-29 22:43:28.748747+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/0e30a6276601af7e5fc4d5166e2e3d37/torch_compile_advanced_usage.py	2025-01-29 22:43:53.434876+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_advanced_usage:

Torch Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/2a9ac10f2667047a7f398d1593b7ca33/torch_export_gpt2.py	2025-01-29 22:43:28.748747+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/2a9ac10f2667047a7f398d1593b7ca33/torch_export_gpt2.py	2025-01-29 22:43:53.451237+00:00
@@ -2,11 +2,12 @@
.. _torch_export_gpt2:

Compiling GPT2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 22:43:28.749747+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 22:43:53.489996+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_resnet:

Compiling ResNet using the Torch-TensorRT Dyanmo Frontend
==========================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/3d4d74f6636d986f33167154f6553961/torch_export_cudagraphs.py	2025-01-29 22:43:28.749747+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/3d4d74f6636d986f33167154f6553961/torch_export_cudagraphs.py	2025-01-29 22:43:53.503968+00:00
@@ -2,11 +2,12 @@
.. _torch_export_cudagraphs:

Torch Export with Cudagraphs
======================================================

-This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well."""
+This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/7b7004dc2ea6f839be532665e16e0426/torch_export_llama2.py	2025-01-29 22:43:28.751747+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/7b7004dc2ea6f839be532665e16e0426/torch_export_llama2.py	2025-01-29 22:43:53.537264+00:00
@@ -2,11 +2,12 @@
.. _torch_export_llama2:

Compiling Llama2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 22:43:28.754747+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 22:43:53.616256+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_advanced_usage:

Dynamo Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/d6e1bb6ec5f884994554d9d12e37a0f6/torch_compile_resnet_example.py	2025-01-29 22:43:28.753747+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/d6e1bb6ec5f884994554d9d12e37a0f6/torch_compile_resnet_example.py	2025-01-29 22:43:53.619172+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_resnet:

Compiling ResNet with dynamic shapes using the `torch.compile` backend
==========================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/dfa60e8f9850fd7761f3e7da81304d32/torch_compile_transformers_example.py	2025-01-29 22:43:28.754747+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/dfa60e8f9850fd7761f3e7da81304d32/torch_compile_transformers_example.py	2025-01-29 22:43:53.621111+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling BERT using the `torch.compile` backend
==============================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 22:43:28.754747+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 22:43:53.661691+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling a Transformer using torch.compile and TensorRT
==============================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 22:43:29.208753+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 22:43:53.668668+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_resnet:

Compiling ResNet using the Torch-TensorRT Dyanmo Frontend
==========================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 22:43:29.208753+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 22:43:53.685452+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_advanced_usage:

Dynamo Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 22:43:29.208753+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 22:43:53.705429+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling a Transformer using torch.compile and TensorRT
==============================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_advanced_usage.py	2025-01-29 22:43:29.238754+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_advanced_usage.py	2025-01-29 22:43:53.847072+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_advanced_usage:

Torch Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_resnet_example.py	2025-01-29 22:43:29.238754+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_resnet_example.py	2025-01-29 22:43:53.895708+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_resnet:

Compiling ResNet with dynamic shapes using the `torch.compile` backend
==========================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_transformers_example.py	2025-01-29 22:43:29.238754+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_transformers_example.py	2025-01-29 22:43:53.910790+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling BERT using the `torch.compile` backend
==============================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_gpt2.py	2025-01-29 22:43:29.238754+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_gpt2.py	2025-01-29 22:43:53.913547+00:00
@@ -2,11 +2,12 @@
.. _torch_export_gpt2:

Compiling GPT2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_cudagraphs.py	2025-01-29 22:43:29.238754+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_cudagraphs.py	2025-01-29 22:43:53.927156+00:00
@@ -2,11 +2,12 @@
.. _torch_export_cudagraphs:

Torch Export with Cudagraphs
======================================================

-This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well."""
+This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_llama2.py	2025-01-29 22:43:29.238754+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_llama2.py	2025-01-29 22:43:53.942999+00:00
@@ -2,11 +2,12 @@
.. _torch_export_llama2:

Compiling Llama2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_Input.py	2025-01-29 22:43:29.247754+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_Input.py	2025-01-29 22:43:54.376459+00:00
@@ -259,11 +259,11 @@
        else:
            return False

    @staticmethod
    def _parse_tensor_domain(
-        domain: Optional[Tuple[float, float]]
+        domain: Optional[Tuple[float, float]],
    ) -> Tuple[float, float]:
        """
        Produce a tuple of integers which specifies a tensor domain in the interval format: [lo, hi)

        Args:
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/_TRTBuilderMonitor.py	2025-01-29 22:43:29.249754+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/_TRTBuilderMonitor.py	2025-01-29 22:43:54.662593+00:00
@@ -51,17 +51,17 @@

    def _redraw(self, *, blank_lines: int = 0) -> None:
        if self._render:

            def clear_line() -> None:
-                print("\x1B[2K", end="")
+                print("\x1b[2K", end="")

            def move_to_start_of_line() -> None:
-                print("\x1B[0G", end="")
+                print("\x1b[0G", end="")

            def move_cursor_up(lines: int) -> None:
-                print("\x1B[{}A".format(lines), end="")
+                print("\x1b[{}A".format(lines), end="")

            def progress_bar(steps: int, num_steps: int) -> str:
                INNER_WIDTH = 10
                completed_bar_chars = int(INNER_WIDTH * steps / float(num_steps))
                return "[{}{}]".format(
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_enums.py	2025-01-29 22:43:29.248754+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_enums.py	2025-01-29 22:43:54.859980+00:00
@@ -1198,11 +1198,11 @@
            "Provided unsupported source type for EngineCapability conversion"
        )

    @classmethod
    def try_from(
-        c: Union[trt.EngineCapability, EngineCapability]
+        c: Union[trt.EngineCapability, EngineCapability],
    ) -> Optional[EngineCapability]:
        """Create a Torch-TensorRT engine capability enum from a TensorRT engine capability enum.

        Takes a device type enum from tensorrt and create a ``torch_tensorrt.EngineCapability``.
        If the source is not supported or the engine capability level is not supported in Torch-TensorRT,
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/impl/activation/ops.py	2025-01-29 22:43:29.250754+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/impl/activation/ops.py	2025-01-29 22:43:55.075638+00:00
@@ -245,11 +245,11 @@
    beta: float,
) -> TRTTensor:
    operation_type = trt.ActivationType.HARD_SIGMOID

    def hard_sigmoid_dyn_range_fn(
-        dyn_range: Tuple[float, float]
+        dyn_range: Tuple[float, float],
    ) -> Tuple[float, float]:
        def hard_sigmoid_fn(x: float) -> float:
            return max(0, min(1, alpha * x + beta))

        return hard_sigmoid_fn(dyn_range[0]), hard_sigmoid_fn(dyn_range[1])
@@ -308,11 +308,11 @@
    alpha: float,
) -> TRTTensor:
    operation_type = trt.ActivationType.THRESHOLDED_RELU

    def thresholded_relu_dyn_range_fn(
-        dyn_range: Tuple[float, float]
+        dyn_range: Tuple[float, float],
    ) -> Tuple[float, float]:
        def thresholded_relu_fn(x: float) -> float:
            return x if x > alpha else 0

        return thresholded_relu_fn(dyn_range[0]), thresholded_relu_fn(dyn_range[1])
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/utils.py	2025-01-29 22:43:29.255754+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/utils.py	2025-01-29 22:43:56.503115+00:00
@@ -463,11 +463,11 @@
    else:
        return torch.device(device)


def to_torch_tensorrt_device(
-    device: Optional[Union[Device, torch.device, str]]
+    device: Optional[Union[Device, torch.device, str]],
) -> Device:
    """Cast a device-type to torch_tensorrt.Device

    Returns the corresponding torch_tensorrt.Device
    """
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/test/converters/acc_op/test_where.py	2025-01-29 22:43:29.260754+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/test/converters/acc_op/test_where.py	2025-01-29 22:43:57.436752+00:00
@@ -99,11 +99,11 @@
                self.y = torch.ones(y_shape)

            def forward(self, condition):
                return torch.where(condition, self.x, self.y)

-        inputs = [(torch.randn(condition_shape) > 0)]
+        inputs = [torch.randn(condition_shape) > 0]
        self.run_test(
            Where(x_shape, y_shape),
            inputs,
            expected_ops={acc_ops.where},
            test_implicit_batch_dim=False,
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/tracer/acc_tracer/acc_tracer.py	2025-01-29 22:43:29.263754+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/tracer/acc_tracer/acc_tracer.py	2025-01-29 22:43:58.457952+00:00
@@ -515,11 +515,11 @@
    dim0 = cast(int, transpose_node.args[1])
    dim1 = cast(int, transpose_node.args[2])
    changed = False

    def _calculate_dim(
-        transpose_dim: Union[torch.fx.Node, int]
+        transpose_dim: Union[torch.fx.Node, int],
    ) -> Union[torch.fx.Node, int]:
        nonlocal transpose_input_node
        nonlocal changed
        if isinstance(transpose_dim, torch.fx.Node):
            # Transpose dim is sub node

Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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

diff --git a/home/runner/work/TensorRT/TensorRT/core/conversion/converters/impl/batch_norm.cpp b/tmp/changes.txt
index 3fe9ec0..c8ec197 100644
--- a/home/runner/work/TensorRT/TensorRT/core/conversion/converters/impl/batch_norm.cpp
+++ b/tmp/changes.txt
@@ -134,7 +134,6 @@ auto batch_norm_registrations TORCHTRT_UNUSED =

              auto eps = static_cast<float>(args[7].unwrapToDouble(1e-5f));

-
              auto scales = at::ones(shape[1], options);
              if (!args[1].IValue()->isNone()) {
                scales = args[1].unwrapToTensor(at::ones(shape[1], options)).cpu().contiguous();
ERROR: Some files do not conform to style guidelines

Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/0e30a6276601af7e5fc4d5166e2e3d37/torch_compile_advanced_usage.py	2025-01-29 23:05:16.424495+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/0e30a6276601af7e5fc4d5166e2e3d37/torch_compile_advanced_usage.py	2025-01-29 23:05:42.059025+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_advanced_usage:

Torch Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/2a9ac10f2667047a7f398d1593b7ca33/torch_export_gpt2.py	2025-01-29 23:05:16.424495+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/2a9ac10f2667047a7f398d1593b7ca33/torch_export_gpt2.py	2025-01-29 23:05:42.079457+00:00
@@ -2,11 +2,12 @@
.. _torch_export_gpt2:

Compiling GPT2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 23:05:16.425495+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 23:05:42.117351+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_resnet:

Compiling ResNet using the Torch-TensorRT Dyanmo Frontend
==========================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/3d4d74f6636d986f33167154f6553961/torch_export_cudagraphs.py	2025-01-29 23:05:16.425495+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/3d4d74f6636d986f33167154f6553961/torch_export_cudagraphs.py	2025-01-29 23:05:42.132395+00:00
@@ -2,11 +2,12 @@
.. _torch_export_cudagraphs:

Torch Export with Cudagraphs
======================================================

-This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well."""
+This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/7b7004dc2ea6f839be532665e16e0426/torch_export_llama2.py	2025-01-29 23:05:16.427495+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/7b7004dc2ea6f839be532665e16e0426/torch_export_llama2.py	2025-01-29 23:05:42.161593+00:00
@@ -2,11 +2,12 @@
.. _torch_export_llama2:

Compiling Llama2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 23:05:16.429495+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 23:05:42.241972+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_advanced_usage:

Dynamo Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/dfa60e8f9850fd7761f3e7da81304d32/torch_compile_transformers_example.py	2025-01-29 23:05:16.429495+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/dfa60e8f9850fd7761f3e7da81304d32/torch_compile_transformers_example.py	2025-01-29 23:05:42.242309+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling BERT using the `torch.compile` backend
==============================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/d6e1bb6ec5f884994554d9d12e37a0f6/torch_compile_resnet_example.py	2025-01-29 23:05:16.429495+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/d6e1bb6ec5f884994554d9d12e37a0f6/torch_compile_resnet_example.py	2025-01-29 23:05:42.255066+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_resnet:

Compiling ResNet with dynamic shapes using the `torch.compile` backend
==========================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 23:05:16.429495+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 23:05:42.292971+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling a Transformer using torch.compile and TensorRT
==============================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 23:05:16.876503+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-29 23:05:42.297565+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_resnet:

Compiling ResNet using the Torch-TensorRT Dyanmo Frontend
==========================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 23:05:16.876503+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-29 23:05:42.314008+00:00
@@ -2,11 +2,12 @@
.. _dynamo_compile_advanced_usage:

Dynamo Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.dynamo.compile` works, and how it integrates with the new `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 23:05:16.876503+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-29 23:05:42.339552+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling a Transformer using torch.compile and TensorRT
==============================================================

-This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model."""
+This interactive script is intended as a sample of the `torch_tensorrt.dynamo.compile` workflow on a transformer-based model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_advanced_usage.py	2025-01-29 23:05:16.906504+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_advanced_usage.py	2025-01-29 23:05:42.469803+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_advanced_usage:

Torch Compile Advanced Usage
======================================================

-This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API."""
+This interactive script is intended as an overview of the process by which `torch_tensorrt.compile(..., ir="torch_compile", ...)` works, and how it integrates with the `torch.compile` API.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_transformers_example.py	2025-01-29 23:05:16.906504+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_transformers_example.py	2025-01-29 23:05:42.530092+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_transformer:

Compiling BERT using the `torch.compile` backend
==============================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a BERT model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_resnet_example.py	2025-01-29 23:05:16.906504+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_resnet_example.py	2025-01-29 23:05:42.535406+00:00
@@ -2,11 +2,12 @@
.. _torch_compile_resnet:

Compiling ResNet with dynamic shapes using the `torch.compile` backend
==========================================================

-This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model."""
+This interactive script is intended as a sample of the Torch-TensorRT workflow with `torch.compile` on a ResNet model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_gpt2.py	2025-01-29 23:05:16.906504+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_gpt2.py	2025-01-29 23:05:42.537265+00:00
@@ -2,11 +2,12 @@
.. _torch_export_gpt2:

Compiling GPT2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular GPT2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_cudagraphs.py	2025-01-29 23:05:16.906504+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_cudagraphs.py	2025-01-29 23:05:42.547969+00:00
@@ -2,11 +2,12 @@
.. _torch_export_cudagraphs:

Torch Export with Cudagraphs
======================================================

-This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well."""
+This interactive script is intended as an overview of the process by which the Torch-TensorRT Cudagraphs integration can be used in the `ir="dynamo"` path. The functionality works similarly in the `torch.compile` path as well.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

--- /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_llama2.py	2025-01-29 23:05:16.906504+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_llama2.py	2025-01-29 23:05:42.574980+00:00
@@ -2,11 +2,12 @@
.. _torch_export_llama2:

Compiling Llama2 using the dynamo backend
==========================================================

-This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model."""
+This script illustrates Torch-TensorRT workflow with dynamo backend on popular Llama2 model.
+"""

# %%
# Imports and Model Definition
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
import torch
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_Input.py	2025-01-29 23:05:16.915504+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_Input.py	2025-01-29 23:05:43.049355+00:00
@@ -259,11 +259,11 @@
        else:
            return False

    @staticmethod
    def _parse_tensor_domain(
-        domain: Optional[Tuple[float, float]]
+        domain: Optional[Tuple[float, float]],
    ) -> Tuple[float, float]:
        """
        Produce a tuple of integers which specifies a tensor domain in the interval format: [lo, hi)

        Args:
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/_TRTBuilderMonitor.py	2025-01-29 23:05:16.917504+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/_TRTBuilderMonitor.py	2025-01-29 23:05:43.292123+00:00
@@ -51,17 +51,17 @@

    def _redraw(self, *, blank_lines: int = 0) -> None:
        if self._render:

            def clear_line() -> None:
-                print("\x1B[2K", end="")
+                print("\x1b[2K", end="")

            def move_to_start_of_line() -> None:
-                print("\x1B[0G", end="")
+                print("\x1b[0G", end="")

            def move_cursor_up(lines: int) -> None:
-                print("\x1B[{}A".format(lines), end="")
+                print("\x1b[{}A".format(lines), end="")

            def progress_bar(steps: int, num_steps: int) -> str:
                INNER_WIDTH = 10
                completed_bar_chars = int(INNER_WIDTH * steps / float(num_steps))
                return "[{}{}]".format(
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_enums.py	2025-01-29 23:05:16.915504+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_enums.py	2025-01-29 23:05:43.540905+00:00
@@ -1198,11 +1198,11 @@
            "Provided unsupported source type for EngineCapability conversion"
        )

    @classmethod
    def try_from(
-        c: Union[trt.EngineCapability, EngineCapability]
+        c: Union[trt.EngineCapability, EngineCapability],
    ) -> Optional[EngineCapability]:
        """Create a Torch-TensorRT engine capability enum from a TensorRT engine capability enum.

        Takes a device type enum from tensorrt and create a ``torch_tensorrt.EngineCapability``.
        If the source is not supported or the engine capability level is not supported in Torch-TensorRT,
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/impl/activation/ops.py	2025-01-29 23:05:16.918504+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/impl/activation/ops.py	2025-01-29 23:05:43.688805+00:00
@@ -245,11 +245,11 @@
    beta: float,
) -> TRTTensor:
    operation_type = trt.ActivationType.HARD_SIGMOID

    def hard_sigmoid_dyn_range_fn(
-        dyn_range: Tuple[float, float]
+        dyn_range: Tuple[float, float],
    ) -> Tuple[float, float]:
        def hard_sigmoid_fn(x: float) -> float:
            return max(0, min(1, alpha * x + beta))

        return hard_sigmoid_fn(dyn_range[0]), hard_sigmoid_fn(dyn_range[1])
@@ -308,11 +308,11 @@
    alpha: float,
) -> TRTTensor:
    operation_type = trt.ActivationType.THRESHOLDED_RELU

    def thresholded_relu_dyn_range_fn(
-        dyn_range: Tuple[float, float]
+        dyn_range: Tuple[float, float],
    ) -> Tuple[float, float]:
        def thresholded_relu_fn(x: float) -> float:
            return x if x > alpha else 0

        return thresholded_relu_fn(dyn_range[0]), thresholded_relu_fn(dyn_range[1])
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/utils.py	2025-01-29 23:05:16.922504+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/utils.py	2025-01-29 23:05:45.150564+00:00
@@ -463,11 +463,11 @@
    else:
        return torch.device(device)


def to_torch_tensorrt_device(
-    device: Optional[Union[Device, torch.device, str]]
+    device: Optional[Union[Device, torch.device, str]],
) -> Device:
    """Cast a device-type to torch_tensorrt.Device

    Returns the corresponding torch_tensorrt.Device
    """
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/test/converters/acc_op/test_where.py	2025-01-29 23:05:16.927504+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/test/converters/acc_op/test_where.py	2025-01-29 23:05:46.079855+00:00
@@ -99,11 +99,11 @@
                self.y = torch.ones(y_shape)

            def forward(self, condition):
                return torch.where(condition, self.x, self.y)

-        inputs = [(torch.randn(condition_shape) > 0)]
+        inputs = [torch.randn(condition_shape) > 0]
        self.run_test(
            Where(x_shape, y_shape),
            inputs,
            expected_ops={acc_ops.where},
            test_implicit_batch_dim=False,
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/tracer/acc_tracer/acc_tracer.py	2025-01-29 23:05:16.931504+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/tracer/acc_tracer/acc_tracer.py	2025-01-29 23:05:47.364080+00:00
@@ -515,11 +515,11 @@
    dim0 = cast(int, transpose_node.args[1])
    dim1 = cast(int, transpose_node.args[2])
    changed = False

    def _calculate_dim(
-        transpose_dim: Union[torch.fx.Node, int]
+        transpose_dim: Union[torch.fx.Node, int],
    ) -> Union[torch.fx.Node, int]:
        nonlocal transpose_input_node
        nonlocal changed
        if isinstance(transpose_dim, torch.fx.Node):
            # Transpose dim is sub node

@github-actions github-actions bot added documentation Improvements or additions to documentation component: build system Issues re: Build system component: api [Python] Issues re: Python API component: runtime component: fx component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths labels Jan 29, 2025
Copy link

@github-actions github-actions bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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

diff --git a/home/runner/work/TensorRT/TensorRT/core/conversion/converters/impl/batch_norm.cpp b/tmp/changes.txt
index 3fe9ec0..c8ec197 100644
--- a/home/runner/work/TensorRT/TensorRT/core/conversion/converters/impl/batch_norm.cpp
+++ b/tmp/changes.txt
@@ -134,7 +134,6 @@ auto batch_norm_registrations TORCHTRT_UNUSED =

              auto eps = static_cast<float>(args[7].unwrapToDouble(1e-5f));

-
              auto scales = at::ones(shape[1], options);
              if (!args[1].IValue()->isNone()) {
                scales = args[1].unwrapToTensor(at::ones(shape[1], options)).cpu().contiguous();
ERROR: Some files do not conform to style guidelines

github-actions[bot]

This comment was marked as spam.

github-actions[bot]

This comment was marked as spam.

@peri044 peri044 merged commit f2a38f5 into main Jan 30, 2025
54 of 68 checks passed
peri044 added a commit that referenced this pull request Jan 30, 2025
#3367)

Co-authored-by: Dheeraj Peri <peri.dheeraj@gmail.com>
peri044 added a commit that referenced this pull request Jan 30, 2025
#3367)

Co-authored-by: Dheeraj Peri <peri.dheeraj@gmail.com>
apbose pushed a commit that referenced this pull request Feb 13, 2025
#3367)

Co-authored-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
cla signed component: api [Python] Issues re: Python API component: build system Issues re: Build system component: conversion Issues re: Conversion stage component: converters Issues re: Specific op converters component: core Issues re: The core compiler component: dynamo Issues relating to the `torch.compile` or `torch._dynamo.export` paths component: fx component: runtime component: tests Issues re: Tests documentation Improvements or additions to documentation
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants