-
Notifications
You must be signed in to change notification settings - Fork 365
feat: Implement support for exporting Torch-TensorRT compiled graphs using torch.export serde APIs #2249
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to Python style guidelines
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to C++ style guidelines
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to Python style guidelines
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to C++ style guidelines
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to Python style guidelines
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
All changes to the fx/
directory can be removed and ported to Dynamo if not already present
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to C++ style guidelines
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to Python style guidelines
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to Python style guidelines
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to C++ style guidelines
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to Python style guidelines
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to C++ style guidelines
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to Python style guidelines
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to C++ style guidelines
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to C++ style guidelines
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to Python style guidelines
Signed-off-by: Dheeraj Peri <peri.dheeraj@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to C++ style guidelines
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code conforms to Python style guidelines
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It looks good to me - just added a comment with an idea for a future improvement
def run_shape_analysis( | ||
parent_module: torch.fx.GraphModule, inputs: Sequence[Input] | ||
) -> Tuple[Dict[Any, Sequence[Any]], Dict[Any, Sequence[Any]]]: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think this is okay to leave for now - in the future we may way to try using Torch's ShapeProp
utility to handle this for us
Description
This PR does the following
call_module
submodule nodes intocall_function
nodes and inserts them accordinglygetitem
nodes based on the number of outputs.These
getitem
nodes are required bytorch._export.save/load
to work.call_module
nodesType of change
Please delete options that are not relevant and/or add your own.
Checklist: