Open
Conversation
These FreeLists were responsible for 5.4MiB of allocations per query. This is an excessive amount for systems that may have hundreds or thousands of queries in flight at any particular time. They are now shrunk to 82KiB per query. The sizes were determined by some internal experimentation; they are the smallest sizes that didn't cause reallocations on a typical NER task (for us). YMMV for other tasks.
Author
|
In our internal benchmarks, this increased tagging performance between 10-30X, depending on the size of the CRF. |
Author
|
Furthermore, training time stayed the same, within 0.03%. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
These FreeLists were responsible for 5.4MiB of allocations per query.
This is an excessive amount for systems that may have hundreds or
thousands of queries in flight at any particular time. They are now
shrunk to 82KiB per query.
The sizes were determined by some internal experimentation; they are the
smallest sizes that didn't cause reallocations on a typical NER task
(for us). YMMV for other tasks.