[Cherry-pick] Deprecate torchscript frontend #3376

narendasan · 2025-01-31T19:50:07Z

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

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

Bug fix (non-breaking change which fixes an issue)
New feature (non-breaking change which adds functionality)
Breaking change (fix or feature that would cause existing functionality to not work as expected)
This change requires a documentation update

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 C++ style guidelines:

diff --git a/home/runner/work/TensorRT/TensorRT/cpp/include/torch_tensorrt/ptq.h b/tmp/changes.txt
index ae8aa07..a2f8234 100644
--- a/home/runner/work/TensorRT/TensorRT/cpp/include/torch_tensorrt/ptq.h
+++ b/tmp/changes.txt
@@ -59,7 +59,7 @@ class Int8Calibrator : Algorithm {
   * calibration cache
   * @param use_cache : bool - Whether to use the cache (if it exists)
   */
-   Int8Calibrator(DataLoaderUniquePtr dataloader, const std::string& cache_file_path, bool use_cache)
+  Int8Calibrator(DataLoaderUniquePtr dataloader, const std::string& cache_file_path, bool use_cache)
      : dataloader_(dataloader.get()), cache_file_path_(cache_file_path), use_cache_(use_cache) {
    for (auto batch : *dataloader_) {
      batched_data_.push_back(batch.data);
@@ -343,7 +343,8 @@ TORCH_TENSORRT_PTQ_DEPRECATION inline Int8Calibrator<Algorithm, DataLoader> make
 * @return Int8CacheCalibrator<Algorithm>
 */
template <typename Algorithm = nvinfer1::IInt8EntropyCalibrator2>
-TORCH_TENSORRT_PTQ_DEPRECATION inline Int8CacheCalibrator<Algorithm> make_int8_cache_calibrator(const std::string& cache_file_path) {
+TORCH_TENSORRT_PTQ_DEPRECATION inline Int8CacheCalibrator<Algorithm> make_int8_cache_calibrator(
+    const std::string& cache_file_path) {
  return Int8CacheCalibrator<Algorithm>(cache_file_path);
}

diff --git a/home/runner/work/TensorRT/TensorRT/cpp/include/torch_tensorrt/macros.h b/tmp/changes.txt
index 5fce518..bdc25f6 100644
--- a/home/runner/work/TensorRT/TensorRT/cpp/include/torch_tensorrt/macros.h
+++ b/tmp/changes.txt
@@ -30,7 +30,9 @@
  STR(TORCH_TENSORRT_MAJOR_VERSION) \
  "." STR(TORCH_TENSORRT_MINOR_VERSION) "." STR(TORCH_TENSORRT_PATCH_VERSION)

-#define TORCH_TENSORRT_PTQ_DEPRECATION [[deprecated("Int8 PTQ Calibrator has been deprecated by TensorRT, please plan on porting to a NVIDIA Model Optimizer Toolkit based workflow. See: https://pytorch.org/TensorRT/tutorials/_rendered_examples/dynamo/vgg16_ptq.html for more details")]]
+#define TORCH_TENSORRT_PTQ_DEPRECATION \
+  [[deprecated(                        \
+      "Int8 PTQ Calibrator has been deprecated by TensorRT, please plan on porting to a NVIDIA Model Optimizer Toolkit based workflow. See: https://pytorch.org/TensorRT/tutorials/_rendered_examples/dynamo/vgg16_ptq.html for more details")]]
// Setup namespace aliases for ease of use
namespace torch_tensorrt {
namespace torchscript {}
ERROR: Some files do not conform to style guidelines

github-actions

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	2025-01-31 19:50:20.576160+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/0e30a6276601af7e5fc4d5166e2e3d37/torch_compile_advanced_usage.py	2025-01-31 19:50:41.152248+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	2025-01-31 19:50:20.576160+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/2a9ac10f2667047a7f398d1593b7ca33/torch_export_gpt2.py	2025-01-31 19:50:41.171830+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	2025-01-31 19:50:20.577160+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-31 19:50:41.212485+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	2025-01-31 19:50:20.576160+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/3d4d74f6636d986f33167154f6553961/torch_export_cudagraphs.py	2025-01-31 19:50:41.223331+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	2025-01-31 19:50:20.579160+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/7b7004dc2ea6f839be532665e16e0426/torch_export_llama2.py	2025-01-31 19:50:41.258447+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	2025-01-31 19:50:20.581160+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-31 19:50:41.336474+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	2025-01-31 19:50:20.581160+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/dfa60e8f9850fd7761f3e7da81304d32/torch_compile_transformers_example.py	2025-01-31 19:50:41.342496+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	2025-01-31 19:50:20.581160+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/d6e1bb6ec5f884994554d9d12e37a0f6/torch_compile_resnet_example.py	2025-01-31 19:50:41.347776+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	2025-01-31 19:50:20.581160+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-31 19:50:41.382135+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	2025-01-31 19:50:21.027168+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-31 19:50:41.390556+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	2025-01-31 19:50:21.028168+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-31 19:50:41.406058+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	2025-01-31 19:50:21.028168+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-31 19:50:41.431367+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	2025-01-31 19:50:21.058168+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_advanced_usage.py	2025-01-31 19:50:41.568970+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	2025-01-31 19:50:21.058168+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_resnet_example.py	2025-01-31 19:50:41.626180+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	2025-01-31 19:50:21.058168+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_gpt2.py	2025-01-31 19:50:41.634355+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_compile_transformers_example.py	2025-01-31 19:50:21.058168+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_transformers_example.py	2025-01-31 19:50:41.636329+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	2025-01-31 19:50:21.058168+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_cudagraphs.py	2025-01-31 19:50:41.642891+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	2025-01-31 19:50:21.058168+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_llama2.py	2025-01-31 19:50:41.669999+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	2025-01-31 19:50:21.067168+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_Input.py	2025-01-31 19:50:42.159875+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	2025-01-31 19:50:21.069168+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/_TRTBuilderMonitor.py	2025-01-31 19:50:42.400111+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	2025-01-31 19:50:21.067168+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_enums.py	2025-01-31 19:50:42.614275+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	2025-01-31 19:50:21.070168+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/impl/activation/ops.py	2025-01-31 19:50:42.810294+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	2025-01-31 19:50:21.074168+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/utils.py	2025-01-31 19:50:44.231147+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	2025-01-31 19:50:21.079169+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/test/converters/acc_op/test_where.py	2025-01-31 19:50:45.210083+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	2025-01-31 19:50:21.083169+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/tracer/acc_tracer/acc_tracer.py	2025-01-31 19:50:46.241591+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
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/ts/ptq.py	2025-01-31 19:50:21.084169+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/ts/ptq.py	2025-01-31 19:50:46.634350+00:00
@@ -91,11 +91,11 @@

    def __new__(cls, *args: Any, **kwargs: Any) -> Self:
        warnings.warn(
            "Int8 PTQ Calibrator has been deprecated by TensorRT, please plan on porting to a NVIDIA Model Optimizer Toolkit based workflow. See: https://pytorch.org/TensorRT/tutorials/_rendered_examples/dynamo/vgg16_ptq.html for more details",
            DeprecationWarning,
-            stacklevel=2
+            stacklevel=2,
        )
        dataloader = args[0]
        algo_type = kwargs.get("algo_type", CalibrationAlgo.ENTROPY_CALIBRATION_2)
        cache_file = kwargs.get("cache_file", None)
        use_cache = kwargs.get("use_cache", False)
@@ -183,11 +183,11 @@

    def __new__(cls, *args: Any, **kwargs: Any) -> Self:
        warnings.warn(
            "Int8 PTQ Calibrator has been deprecated by TensorRT, please plan on porting to a NVIDIA Model Optimizer Toolkit based workflow. See: https://pytorch.org/TensorRT/tutorials/_rendered_examples/dynamo/vgg16_ptq.html for more details",
            DeprecationWarning,
-            stacklevel=2
+            stacklevel=2,
        )
        cache_file = args[0]
        algo_type = kwargs.get("algo_type", CalibrationAlgo.ENTROPY_CALIBRATION_2)

        if os.path.isfile(cache_file):
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/ts/_compiler.py	2025-01-31 19:50:21.084169+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/ts/_compiler.py	2025-01-31 19:50:46.805755+00:00
@@ -104,11 +104,11 @@
    """

    warnings.warn(
        'The torchscript frontend for Torch-TensorRT has been deprecated, please plan on porting to the dynamo frontend (torch_tensorrt.compile(..., ir="dynamo"). Torchscript will continue to be a supported deployment format via post compilation torchscript tracing, see: https://pytorch.org/TensorRT/user_guide/saving_models.html for more details',
        DeprecationWarning,
-        stacklevel=2
+        stacklevel=2,
    )

    input_list = list(inputs) if inputs is not None else []
    enabled_precisions_set = (
        enabled_precisions if enabled_precisions is not None else set()
@@ -248,11 +248,11 @@
        bytes: Serialized TensorRT engine, can either be saved to a file or deserialized via TensorRT APIs
    """
    warnings.warn(
        'The torchscript frontend for Torch-TensorRT has been deprecated, please plan on porting to the dynamo frontend (torch_tensorrt.convert_method_to_trt_engine(..., ir="dynamo"). Torchscript will continue to be a supported deployment format via post compilation torchscript tracing, see: https://pytorch.org/TensorRT/user_guide/saving_models.html for more details',
        DeprecationWarning,
-        stacklevel=2
+        stacklevel=2,
    )

    input_list = list(inputs) if inputs is not None else []
    enabled_precisions_set = (
        enabled_precisions if enabled_precisions is not None else {torch.float}

github-actions

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	2025-01-31 19:57:05.796040+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/0e30a6276601af7e5fc4d5166e2e3d37/torch_compile_advanced_usage.py	2025-01-31 19:57:27.751982+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	2025-01-31 19:57:05.796040+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/2a9ac10f2667047a7f398d1593b7ca33/torch_export_gpt2.py	2025-01-31 19:57:27.776814+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	2025-01-31 19:57:05.797040+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-31 19:57:27.812209+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	2025-01-31 19:57:05.797040+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/3d4d74f6636d986f33167154f6553961/torch_export_cudagraphs.py	2025-01-31 19:57:27.825791+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	2025-01-31 19:57:05.799040+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/7b7004dc2ea6f839be532665e16e0426/torch_export_llama2.py	2025-01-31 19:57:27.859322+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	2025-01-31 19:57:05.802040+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-31 19:57:27.940286+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	2025-01-31 19:57:05.801040+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/dfa60e8f9850fd7761f3e7da81304d32/torch_compile_transformers_example.py	2025-01-31 19:57:27.943549+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	2025-01-31 19:57:05.801040+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/d6e1bb6ec5f884994554d9d12e37a0f6/torch_compile_resnet_example.py	2025-01-31 19:57:27.951805+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	2025-01-31 19:57:05.802040+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-31 19:57:27.985761+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	2025-01-31 19:57:06.254041+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/418941399c146271a7b7728ba3059960/dynamo_compile_resnet_example.py	2025-01-31 19:57:27.995944+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	2025-01-31 19:57:06.254041+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e1ef5a42560a98a132f56a79d0b66f79/dynamo_compile_advanced_usage.py	2025-01-31 19:57:28.013231+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	2025-01-31 19:57:06.254041+00:00
+++ /home/runner/work/TensorRT/TensorRT/docs/v1.4.0/_downloads/e550c5f53cc43e11aa6da8cfb79b54df/dynamo_compile_transformers_example.py	2025-01-31 19:57:28.032424+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	2025-01-31 19:57:06.284042+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_advanced_usage.py	2025-01-31 19:57:28.204136+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	2025-01-31 19:57:06.284042+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_resnet_example.py	2025-01-31 19:57:28.241527+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	2025-01-31 19:57:06.284042+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_compile_transformers_example.py	2025-01-31 19:57:28.240301+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	2025-01-31 19:57:06.285042+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_gpt2.py	2025-01-31 19:57:28.249558+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	2025-01-31 19:57:06.284042+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_cudagraphs.py	2025-01-31 19:57:28.256034+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	2025-01-31 19:57:06.285042+00:00
+++ /home/runner/work/TensorRT/TensorRT/examples/dynamo/torch_export_llama2.py	2025-01-31 19:57:28.288288+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	2025-01-31 19:57:06.294042+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_Input.py	2025-01-31 19:57:28.720332+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	2025-01-31 19:57:06.295042+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/_TRTBuilderMonitor.py	2025-01-31 19:57:29.027501+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	2025-01-31 19:57:06.294042+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/_enums.py	2025-01-31 19:57:29.266942+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	2025-01-31 19:57:06.296041+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/conversion/impl/activation/ops.py	2025-01-31 19:57:29.445807+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	2025-01-31 19:57:06.301042+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/utils.py	2025-01-31 19:57:30.911942+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	2025-01-31 19:57:06.306042+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/test/converters/acc_op/test_where.py	2025-01-31 19:57:31.830548+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	2025-01-31 19:57:06.310042+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/fx/tracer/acc_tracer/acc_tracer.py	2025-01-31 19:57:33.227199+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

facebook-github-bot added the cla signed label Jan 31, 2025

github-actions bot added component: api [Python] Issues re: Python API component: api [C++] Issues re: C++ API labels Jan 31, 2025

github-actions bot requested a review from peri044 January 31, 2025 19:50

github-actions bot requested changes Jan 31, 2025

View reviewed changes

Deprecate torchscript frontend

79d7e7c

narendasan force-pushed the deprecate_ts_2.6 branch from 10a519e to 79d7e7c Compare January 31, 2025 19:56

github-actions bot requested changes Jan 31, 2025

View reviewed changes

narendasan merged commit c7d610a into release/2.6 Jan 31, 2025
67 of 68 checks passed

narendasan deleted the deprecate_ts_2.6 branch January 31, 2025 21:12

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Cherry-pick] Deprecate torchscript frontend #3376

[Cherry-pick] Deprecate torchscript frontend #3376

narendasan commented Jan 31, 2025

github-actions bot left a comment

github-actions bot left a comment

github-actions bot left a comment

[Cherry-pick] Deprecate torchscript frontend #3376

[Cherry-pick] Deprecate torchscript frontend #3376

Conversation

narendasan commented Jan 31, 2025

Description

Type of change

Checklist:

github-actions bot left a comment

Choose a reason for hiding this comment

github-actions bot left a comment

Choose a reason for hiding this comment

github-actions bot left a comment

Choose a reason for hiding this comment