Fix vLLM generation with sampling params #578
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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
lewtun
commented
Feb 21, 2025
| @@ -138,6 +139,8 @@ def vllm( | |||
| generation_parameters = GenerationParameters.from_dict(config) | |||
| else: | |||
| generation_parameters = GenerationParameters.from_model_args(model_args) | |||
| # We slice out generation_parameters from model_args to avoid double-counting in the VLLMModelConfig | |||
| model_args = re.sub(r"generation_parameters=\{.*?\},?", "", model_args).strip(",") | |||
There was a problem hiding this comment.
This is a bit hacky, so am open to other ideas!
There was a problem hiding this comment.
Works for me for now, I trust you debuggued it - but can you create an issue so we don't forget to upgrade to something more robust?
lewtun
commented
Feb 21, 2025
clefourrier
reviewed
Feb 21, 2025
clefourrier
approved these changes
Feb 21, 2025
|
feel free to merge once tests are go again :) |
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Outdated suggestions cannot be applied.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.
This PR fixes a bug where it was not possible to pass
generation_parameterstolighteval vllmdue to:The root cause was due to
model_argscontaininggeneration_parametersafter we extracted them.