Description
Bug Description
https://github.com/pytorch/TensorRT/actions/runs/15925323279/job/44922466608
runtime/test_mutable_torchtrt_module.py:118:
/opt/python/cp39-cp39/lib/python3.9/site-packages/torch_tensorrt/dynamo/_compiler.py:696: in compile
exported_program = exported_program.run_decompositions(
/opt/python/cp39-cp39/lib/python3.9/site-packages/torch/export/exported_program.py:123: in wrapper
return fn(*args, **kwargs)
/opt/python/cp39-cp39/lib/python3.9/site-packages/torch/export/exported_program.py:1514: in run_decompositions
return _decompose_exported_program(
/opt/python/cp39-cp39/lib/python3.9/site-packages/torch/export/exported_program.py:955: in _decompose_exported_program
) = _decompose_and_get_gm_with_new_signature_constants(
/opt/python/cp39-cp39/lib/python3.9/site-packages/torch/export/exported_program.py:473: in _decompose_and_get_gm_with_new_signature_constants
aten_export_artifact = _export_to_aten_ir(
/opt/python/cp39-cp39/lib/python3.9/site-packages/torch/export/_trace.py:907: in _export_to_aten_ir
_maybe_fixup_gm_and_output_node_meta(mod, gm)
To Reproduce
Steps to reproduce the behavior:
Expected behavior
Environment
Build information about Torch-TensorRT can be found by turning on debug messages
- Torch-TensorRT Version (e.g. 1.0.0):
- PyTorch Version (e.g. 1.0):
- CPU Architecture:
- OS (e.g., Linux):
- How you installed PyTorch (
conda,pip,libtorch, source): - Build command you used (if compiling from source):
- Are you using local sources or building from archives:
- Python version:
- CUDA version:
- GPU models and configuration:
- Any other relevant information: