Switch grammar backend to Formatron #252
Merged
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
* Replace LMFE's regex and JSON schema filters with Formatron's * Remove Outlines EBNF filter in preparation for Formatron KBNF filter * TODO: Implement Formatron KBNF filter
* Also remove empty cache clear function
Signed-off-by: kingbri <[email protected]>
|
@DocShotgun building KBNF's vocabulary should be around 1 second(though you may want to test out on your own) so lru_cache is needed if you think this is too slow. You may also want to benchmark building a filter out of a reasonably complex json schema and decide whether you want some caches for building filters as well. |
* Avoid rebuilding the KBNF engine vocabulary on every grammar-enabled request
v0.2.6 Signed-off-by: kingbri <[email protected]>
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Outdated suggestions cannot be applied.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.
Is your pull request related to a problem? Please describe.
N/A
Why should this feature be added?
Simplify dependencies and improve grammar-constrained inference performance.
Examples
N/A
Additional context
To-do:
lru_cacheneeded?Other: