Make NewRawInputSequence public to prevent costly reflection #72
Conversation
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
…rary In most cases, users of the api will simply pass a string to the tokenizer to get a list of tokens to pass to the model. In that case, there is no need to call the reflect library at all, which might save important cpu cycles and consequently improve the throughput of the services using the tokenizer library.
|
Hello. Thanks for maintaining this awesome project. I'm about to use the library to compute embeddings in a potentially high throughput scenario, so I thought this optimization might be worth it since it is a low hanging fruit. Please let me know what you think. Thanks. |
clems4ever
changed the title
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Outdated suggestions cannot be applied.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.
In most cases, users of the api will simply pass a string to the tokenizer to get a list of tokens to pass to the model. In that case, there is no need to call the reflect library at all, which might save important cpu cycles and consequently improve the throughput of the services using the tokenizer library. This is an issue for Batch tokenization, not Single tokenization btw.