-
Notifications
You must be signed in to change notification settings - Fork 3k
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
Add QNN EP option context_node_name_prefix to set EPContext node name prefix #21236
Conversation
one still has to glue separate context nodes together in one graph/model right? |
It's hard to have a common script to do the glue work. It's so hard to know what the user want to do. I can imagine there's could be many trick work. |
sync'd with @HectorSVC offline. we agreed that it's probably better to hold off on this PR until the workflow for splitting/gluing back together the model has been finalized. |
Description
Add QNN EP option context_node_name_prefix to set EPContext node name prefix
Motivation and Context
For the case to workaround QNN context PD memory limit, user need split the model into pieces and generate the QNN context model separately. It could happen that the generated EPContext node in separate graph has same node name. This will cause issue if glue those EPContext nodes together into a single model.
To avoid this user can set this context_node_name_prefix for each split pieces to make the node name unique.