feat: Adding multiple tokenizers specification for open ai frontend #8027
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
oandreeva-nv
force-pushed
the
oandreeva_openai_multiple_tokenizers
branch
from
e0bc399 to
aaf4f6d
Compare
oandreeva-nv
changed the title
| lora_names=lora_names, | ||
| tokenizer=self.tokenizer_map.get(name, default_tokenizer), |
There was a problem hiding this comment.
Since the tokenizer technically could be None now, should we add a check in chat method to have tokenizer to not apply_chat_template if this is None and raise an exception.
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Outdated suggestions cannot be applied.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.
What does the PR do?
This PR adds support for using multiple tokenizers in the OpenAI-compatible frontend, allowing different models to use their own specific tokenizers. This is crucial for correctly handling various model architectures and their chat templates.
Implementation
--tokenizerflag to support tokenizer mapping configuration to maintain backward compatibility with single tokenizer setupExample Usage
Checklist
<commit_type>: <Title>Commit Type:
Check the conventional commit type
box here and add the label to the github PR.
Related PRs:
Where should the reviewer start?
Test plan:
Added
TestMultipleTokenizersclass to test the featureCaveats:
Background
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)