[Torch FX] Add Special FX Metatype in Torch Operator Metatypes #2976
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
alexsu52
reviewed
Sep 20, 2024
| @@ -120,15 +135,15 @@ def create_nncf_graph(model: torch.fx.GraphModule) -> PTNNCFGraph: | |||
|
|
|||
| for source_node in model.graph.nodes: | |||
| node_type, node_metatype = GraphConverter._get_node_type_and_metatype(source_node, model) | |||
There was a problem hiding this comment.
Could you suggest how to take function namespace into account when defining metatype?
cc' @daniil-lyakhov @AlexanderDokuchaev
There was a problem hiding this comment.
Alright, I will check for possible ways to map with function namespaces as well.
|
Apparently covered by #2891 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Changes
FXEmbeddingMetatypefor torch FX embedding metatypeReason for changes
The current torch embedding metatype, which maps to
torch.nn.functional.embeddinghas weight node on port 1, but when usingtorch.nn.Embeddingwith torch fx, since it has weight on port 0, the metatype should be defined accordingly.