[FEA] Support configurable indexing and NVE layers for exportable embedding collections - #478
Draft
geoffreyQiu wants to merge 3 commits into
Draft
geoffreyQiu wants to merge 3 commits into
geoffreyQiu wants to merge 3 commits into
Conversation
geoffreyQiu
force-pushed
the
feature/exportable-embedding-table-fusion
branch
from
September 4, 2026 04:35
a63329d to
70063d5
Compare
geoffreyQiu
force-pushed
the
feature/exportable-embedding-table-fusion
branch
14 times, most recently
from
September 17, 2026 10:32
206874d to
a23418e
Compare
geoffreyQiu
force-pushed
the
feature/exportable-embedding-table-fusion
branch
from
September 17, 2026 10:41
a23418e to
2c154a9
Compare
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Extend DynamicEmb exportable inference embedding collections with configurable indexing and NVE storage.
The conversion API now accepts an
InferenceEmbeddingCollectionConfigfor each physical embedding collection instead of selecting the implementation throughuse_dynamic.What changed
FusedIdentityIndexer,LinearHashMapIndexer, andBitConcatIndexer.Verified combinations
FusedIdentityIndexerLinearHashMapIndexerLinearHashMapIndexerLinearHashMapIndexerBitConcatIndexerBitConcatIndexerBitConcatIndexeris intentionally limited to hierarchical layers. Its table-ID and feature-ID bit widths are fixed by the model configuration.Validation
Commit organization
The draft is organized into three commits so it can later be split if needed:
Checklist