[feat + fix] Add normalize_embeddings support to multi-process encoding; fix multi-process encoding on CUDA devices
#2377
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
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Outdated suggestions cannot be applied.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.
Supersedes #2252
Hello!
Pull Request overview
normalize_embeddingssupport to multi-process encodingDetails
The
normalize_embeddingsfunctionality is fairly straightforward - it speaks for itself.The encoding fix not quite so much. When the model is loaded on CUDA and
start_multi_process_poolis called, then the model weights become 0.0 as soon as one of the processes start. There's a tad more info here. This is counteracted when the model is on CPU originally, so I move the model tocpujust prior to starting the encoding. I also use share_memory as it's recommended.Thanks @TeisNP for starting this work!