TorchTensorRTModule Serialization Fix #3572
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
component: api [Python]
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
There was a problem hiding this comment.
There are some changes that do not conform to Python style guidelines:
--- /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/runtime/_TorchTensorRTModule.py 2025-06-13 19:19:30.680941+00:00
+++ /home/runner/work/TensorRT/TensorRT/py/torch_tensorrt/dynamo/runtime/_TorchTensorRTModule.py 2025-06-13 19:19:58.614974+00:00
@@ -225,20 +225,28 @@
return
self.engine = torch.classes.tensorrt.Engine(self._pack_engine_info())
def encode_metadata(self, metadata: Any) -> str:
metadata = copy.deepcopy(metadata)
- metadata["settings"].torch_executed_ops = TorchTensorRTModule.serialize_aten_ops(metadata["settings"].torch_executed_ops)
+ metadata["settings"].torch_executed_ops = (
+ TorchTensorRTModule.serialize_aten_ops(
+ metadata["settings"].torch_executed_ops
+ )
+ )
dumped_metadata = pickle.dumps(metadata)
encoded_metadata = base64.b64encode(dumped_metadata).decode("utf-8")
return encoded_metadata
@staticmethod
def decode_metadata(encoded_metadata: bytes) -> Any:
dumped_metadata = base64.b64decode(encoded_metadata.encode("utf-8"))
metadata = pickle.loads(dumped_metadata)
- metadata["settings"].torch_executed_ops = TorchTensorRTModule.deserialize_aten_ops(metadata["settings"].torch_executed_ops)
+ metadata["settings"].torch_executed_ops = (
+ TorchTensorRTModule.deserialize_aten_ops(
+ metadata["settings"].torch_executed_ops
+ )
+ )
return metadata
@staticmethod
def serialize_aten_ops(aten_ops: Set[torch._ops.OpOverload]) -> Set[str]:
return {str(op) for op in aten_ops}
narendasan
reviewed
Jun 13, 2025
| return metadata | ||
|
|
||
| @staticmethod | ||
| def serialize_aten_ops(aten_ops: Set[torch._ops.OpOverload]) -> Set[str]: |
There was a problem hiding this comment.
call this _serialize_torch_ops
cehongwang
force-pushed
the
cehongwang-patch-1
branch
from
6bf3127 to
f9235ed
Compare
narendasan
reviewed
Jun 13, 2025
narendasan
reviewed
Jun 13, 2025
zewenli98
reviewed
Jun 14, 2025
| @@ -143,6 +144,16 @@ class CompilationSettings: | |||
| use_distributed_mode_trace: bool = USE_DISTRIBUTED_MODE_TRACE | |||
| offload_module_to_cpu: bool = OFFLOAD_MODULE_TO_CPU | |||
|
|
|||
| def __getstate__(self) -> dict[str, Any]: | |||
| state = self.__dict__.copy() | |||
| state["torch_executed_ops"] = {str(op) for op in state["torch_executed_ops"]} | |||
There was a problem hiding this comment.
consider using ConverterRegistry.qualified_name_or_str(target)
cehongwang
force-pushed
the
cehongwang-patch-1
branch
2 times, most recently
from
1f50da4 to
0b3edfe
Compare
narendasan
reviewed
Jun 16, 2025
cehongwang
force-pushed
the
cehongwang-patch-1
branch
from
0b3edfe to
2d7c87f
Compare
narendasan
reviewed
Jun 16, 2025
| @@ -84,6 +84,41 @@ def test_resnet18_cpu_offload(ir): | |||
| torch._dynamo.reset() | |||
|
|
|||
|
|
|||
| @pytest.mark.unit | |||
| def test_resnet18_torch_exec_ops(ir): | |||
There was a problem hiding this comment.
We should also test that you can serialize and deserialize this model right?
narendasan
reviewed
Jun 17, 2025
| @@ -372,6 +372,44 @@ def test_resnet18_dynamic(ir): | |||
| ) | |||
|
|
|||
|
|
|||
| @pytest.mark.unit | |||
| def test_resnet18_dynamic_torch_exec_ops(ir): | |||
There was a problem hiding this comment.
Is this test about dynamic inputs or serialization?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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.
Checklist: