Add features to improve memory usage #63
Merged
+293
−76
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
…5.load` to use that function
… to reload the mmapped scores/corpus, allowing lower memory usage
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Outdated suggestions cannot be applied.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.
Results.mergemethod allowing merging list of resultsget_max_memory_usagecompatible with mac osexamples/index_nq.pyto use numba, new tokenizer, simplify loading datasetexamples/retrieve_nq.pyto use numba, and to record memory usageexamples/retrieve_nq_with_batching.pywhich is a batched version of retrieval that clears memory after every useBM25.load_scoresthat allows loading only the scores of the objectload_vocabparameter set toTrueby default inBM25.load, allowing the vocabulary to not be always loaded.