docs(vllm_performance): use optuna in vLLM performance endpoint example#857
Merged
Merged
Conversation
… use search algorithm from the optuna library Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
AlessandroPomponio
changed the title
michael-johnston
requested changes
Apr 15, 2026
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
michael-johnston
approved these changes
Apr 16, 2026
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 migrates the vLLM performance endpoint example from using HyperOpt to Optuna as the search algorithm, mainly because Optuna is more actively maintained and released.
Using HyperOpt users might incur in runtime errors due to to using deprecated python libraries.
The example is slightly different as in optuna it is not possible to set the gamma value that control the number of top observations to be selected. The rest of the discussion, explaining how the optimizer behaves, is mostly related to the actual sampling algorithm (TPE) and therefore it is valid with both libraries.
This PR fixes #847