Dheeraj Peri

The fixes are already in main. Closing this now. Feel free to re-open if you encounter this.

@apbose is this ready ?

> @peri044 Right now the dynamic input cases are supported, I will add some test cases for dynamic index. Although the implementation should support it. Also, is there any example...

`TestIndexDynamicConstantConverter` tests are failing in CI

The to_copy converter now supports dynamic shapes https://github.com/pytorch/TensorRT/blob/main/py/torch_tensorrt/dynamo/conversion/aten_ops_converters.py#L1109-L1112. Please try with our main branch. If the issue exists, please provide the input shapes to pass to your reproducer for us...

Thanks for catching this. The correct usage is as follows: ```py trt_gm = torch_tensorrt.dynamo.compile(exp_program, inputs) # Run inference trt_gm(*inputs) ``` inputs is already a list and `[inputs]` was being passed...

@AyanamiReiFan I don't know of any workarounds for upgrading TRT 10.3 on Jetpack. That being said, you could give [25.03-py3-igpu](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/pytorch/tags) a container a try. This container has TRT 10.9 and...

@thuyen Our dynamo path supersedes FX path. While the FX frontend isnt actively being developed, any FX components in use are still covered through dynamo tests in `tests/py/dynamo`. You could...

@yjjinjie Can you try with our latest codebase ? I believe this issue should be resolved. I have tried the following script which works. I was unable to run your...

Thanks for pointing this out. This PR has the fix : https://github.com/pytorch/TensorRT/pull/3320. We need this pass instead of the converter because of https://github.com/pytorch/TensorRT/pull/2464