GH-1089: Optimize FlairEmbeddings depending on storage mode #1095
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Outdated suggestions cannot be applied.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.
As discussed in #1089, the
clone()
operation inFlairEmbeddings
is expensive and only required if theembedding_storage_mode
is 'gpu'. However, information of which storage mode is selected is not visible inFlairEmbeddings
. To address this, this PR adds a new global variableembedding_storage_mode
that is set in thestore_embeddings()
method and checked inFlairEmbeddings
. This gives us a roughly 10% improvement in inference speed.The PR also renames the
embeddings_storage_mode
parameter of theevaluate()
functions toembedding_storage_mode
to make it consistent.