Dheeraj Peri

# 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....

# Description * This PR adds module_call_graph to preserve the output spec obtained from the graph module. * This will let exported program know what the output_spec is during it's...

# Description This PR replaces our old shape propagation system which relied on dummy runs of inputs. If the inputs were dynamic, we used to run dummy inference on min,...

# 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....

📖 [Story] Implement dynamic shapes + fallback in dynamo

1

## TL;DR ## Goal(s) ## Tasks ```[tasklist] ### Tasks - [ ] https://github.com/pytorch/TensorRT/issues/2264 - [ ] https://github.com/pytorch/TensorRT/issues/2300 - [ ] https://github.com/pytorch/TensorRT/issues/2308 - [ ] https://github.com/pytorch/TensorRT/issues/2377 - [ ] https://github.com/pytorch/TensorRT/issues/2644 ```...

## Bug Description arange converter fails with ITensor input ``` File "/home/dperi/Downloads/TensorRT/py/torch_tensorrt/dynamo/conversion/_TRTInterpreter.py", line 367, in call_function return converter(self.ctx, target, args, kwargs, self._cur_node_name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/dperi/Downloads/TensorRT/py/torch_tensorrt/dynamo/conversion/ops_evaluators.py", line 49, in aten_ops_arange_start_step return...

**Is your feature request related to a problem? Please describe.** Currently if a network takes an input tensor which is used as shape for other layers in the graph, a...

🐛 [Bug] Cannot perform inference if the ExportedProgram has weighted layers and custom ops.

2

## Bug Description 1) The graph has a conv node in pytorch and a TensorRT node. The conv node has weight and bias lifted as placeholders. Hence we are seeing...

🐛 [Bug] Encountered bug when using Torch-TensorRT MONAI

2

## Bug Description Monai bug swin unet not working. Check nvbugs. Try dynamo ## Expected behavior ## Environment > Build information about Torch-TensorRT can be found by turning on debug...

## TL;DR torch.export has serde API and now supports custom object (in our case `torch.classes.tensorrt.Engine`) serialization. ## Goal(s) We should be able to serialize/deserialize the output of torch-trt compilation. ##...