Improve performance of GPT3Tokenizer #579
Merged
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Outdated suggestions cannot be applied.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.
Motivation and Context
Improve the performance of GPT3Tokenizer in both throughput and allocation.
Description
This primarily focuses on the path once the BPE cache has already been sufficiently warmed up. There's much more that can be done about the code path that warms it up, but I've only handled the low-hanging fruit there for now. This can all also be significantly improved once the project moves to target .NET Core instead of netstandard2.0.
Contribution Checklist
dotnet format