Add logits processors to enable logit_bias in OpenAI server #535
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
This was referenced Sep 29, 2023
Closed
noamgat
reviewed
Oct 31, 2023
|
|
||
| if logits_processors is not None: | ||
| for logits_processor in logits_processors: | ||
| logits = logits_processor(logits, output_tokens) |
Contributor
There was a problem hiding this comment.
In this call, you send output_tokens to logits_processor(). However, in the LogitsProcessor interface, the output_tokens parameter does not exist:
def __call__(self, logits: torch.tensor) -> torch.tensor:
How does it work?
Collaborator
|
Thank you for your PR! Now #1469 is merged with logits_processors API, can you help rebase and use that instead? The |
Contributor
|
@zacharyblank Any update? This will be greate for advanced users. vllm/outlines is nice but nothing beats pure code based state machine when it comes to performance. |
Member
|
Thanks for your contribution. Close this PR as this feature has been supported in #3027. |
rickyyx
added a commit
to rickyyx/vllm
that referenced
this pull request
Oct 7, 2024
Co-authored-by: sang <rkooo567@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
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Outdated suggestions cannot be applied.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.
This PR makes it possible to define custom logits processors to alter the probability of token generation based on user defined code. This allows for the vLLM OpenAI server to accept requests with
logit_biastoo.The BiasLogitsProcessor is included specifically for the OpenAI server to handle requests with
logit_bias.