Return logprobs in delayed_sampling #1323
Merged
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
Signed-off-by: Karol Damaszke <kdamaszke@habana.ai>
madamczyk-intel
approved these changes
May 27, 2025
mswiniarsk
approved these changes
May 27, 2025
mswiniarsk
reviewed
May 27, 2025
Signed-off-by: Karol Damaszke <kdamaszke@habana.ai>
Signed-off-by: Karol Damaszke <kdamaszke@habana.ai>
Signed-off-by: Karol Damaszke <kdamaszke@habana.ai>
|
/run-gaudi-tests |
Signed-off-by: Karol Damaszke <kdamaszke@habana.ai>
kdamaszk
requested review from
kzawora-intel,
michalkuligowski,
mgawarkiewicz-intel,
vivekgoe,
afierka-intel,
xuechendi and
jikunshang
as code owners
|
/run-gaudi-tests |
1 similar comment
|
/run-gaudi-tests |
ccrhx4
pushed a commit
to ccrhx4/huanxing.vllm-fork
that referenced
this pull request
Jul 16, 2025
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Outdated suggestions cannot be applied.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.
Currently when using delayed_sampling we are not updating logprobs. It means that if user will request them through
SamplingParams, he will receiveNone.This PR fixes that by adding calculation of logprobs to sampler postprocessing.