feat: add --disable-prompt-logprobs argument #95
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Outdated suggestions cannot be applied.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.
Description
Adds a new
--disable-prompt-logprobs
boolean argument that defaults to False. When set to True,prompt_logprobs
will always be set toNone
in the SamplingParams, regardless of the incoming request parameters, disabling all usage of prompt logprobs.This flag is being added because computation of prompt logprobs can add latency to request processing and there are a couple of bugs/crashes that occur when using prompt logprobs.
How Has This Been Tested?
Manually tested to verify that the flag can be set via env var and that it has the desired effect to not return prompt logprobs (but still returns logprobs on generated tokens).
Merge criteria: