-
Notifications
You must be signed in to change notification settings - Fork 350
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
feat: Support exporting Torch-TRT compiled Graphmodules #3262
base: lluo/save_remove_inputs
Are you sure you want to change the base?
Conversation
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.
Cant we just reuse the packed format we use for def_pkl?
|
||
# namespace::class_name | ||
@torch._library.register_fake_class("tensorrt::Engine") | ||
class FakeTRTEngine: |
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.
Could we move the TorchTensorRTModule impl here?
@@ -318,6 +318,23 @@ void TRTEngine::verify_serialization_fmt(const std::vector<std::string>& seriali | |||
<< ")"); | |||
} | |||
|
|||
FlattenedState TRTEngine::__obj_flatten__() { |
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.
Im not sure why this needs to be a method vs reusing the functions in register_jit_hooks
What is the spec for flattened_obj? |
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.
Fixes # (issue)
Type of change
Please delete options that are not relevant and/or add your own.
Checklist: