feat: limit tokenizers cache size #3577
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
dosubot
bot
added
the
size:L
StanGirard
reviewed
Jan 29, 2025
| _cache: dict[ | ||
| int, tuple["LLMTokenizer", int, float] | ||
| ] = {} # {hash: (tokenizer, size_bytes, last_access_time)} | ||
| _max_cache_size_mb: int = 50 |
There was a problem hiding this comment.
Tu peux mettre un peu plus gros je pense - 100MB par exemple
StanGirard
deleted the
feature/ent-524-implement-lru-cache-tokenizer-max-size-3
branch
StanGirard
added a commit
that referenced
this pull request
Jan 30, 2025
🤖 I have created a release *beep* *boop* --- ## [0.0.31](core-0.0.30...core-0.0.31) (2025-01-30) ### Features * cache tokenizers ([#3558](#3558)) ([699dc2e](699dc2e)) * limit tokenizers cache size ([#3577](#3577)) ([e2a3bcb](e2a3bcb)) * remove pympler dependency and add better way to calculate size of tokenizer cache ([#3580](#3580)) ([2fbd5d4](2fbd5d4)) * remove tokenizer load ([#3576](#3576)) ([05e212a](05e212a)) --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please).
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Outdated suggestions cannot be applied.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.
We limit the number of preloaded tokenizers to 3 and the maximum size to 50 MB