This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
[v1.x][BUGFIX] Export attributes of transformer operators #20555
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Outdated suggestions cannot be applied.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.
Description
sg_mkldnn_selfatt_qk and sg_mkldnn_selfatt_valatt ops, when not quantized, are not exporting their attributes to the *-symbol.json file, thus making the SymbolBlock.imports/model.load_checkpoint functions crash with an error: "mxnet.base.MXNetError: MXNetError: Required parameter heads of int is not presented, in operator sg_mkldnn_selfatt_*(name="sg_mkldnn_selfatt_*")" when trying to load a model that uses them.
This change fixes this issue.
Checklist
Essentials
Changes