🐛 [Bug] scaled_dot_product_attention test in Torchscript failure

[peri044]

Bug Description

//tests/core/conversion/converters:test_scaled_dot_product_attention (C++ exception with description "0 INTERNAL ASSERT FAILED at "../torch/csrc/jit/ir/alias_analysis.cpp":615, please report a bug to PyTorch. We don't have an op for aten::scaled_dot_product_attention but it isn't a special case. Argument types: Tensor, Tensor, Tensor, Tensor, float, bool, )

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:

Additional context

[peri044]

Hello @mfeliz-cruise @andi4191, have you seen this error or does it pass your test suite ? Internally, others also reported this converter test failure, so I wanted to double check.

[mfeliz-cruise]

Probably a PyTorch version mismatch. I think the interface of scaled_dot_product_attention may have changed to add the %scale in 2.2.