fix(vllm): handle `logprobs=None´ and align logprob docs#5203
Open
LeonEricsson wants to merge 3 commits intohuggingface:mainfrom
Open
fix(vllm): handle `logprobs=None´ and align logprob docs#5203LeonEricsson wants to merge 3 commits intohuggingface:mainfrom
LeonEricsson wants to merge 3 commits intohuggingface:mainfrom
Conversation
LeonEricsson
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 fixes logprob handling and aligns the related documentation.
trl/scripts/vllm_serve.pynow acceptsNoneforlogprobsandlogprob_token_idsin/generate/and/chat/responses, discussed here. This prevents server 500s when requests uselogprobs=Noneand vLLM returns no logprob payload.It also updates logprob docstrings in
trl/generation/vllm_client.py,trl/scripts/vllm_serve.py,trl/generation/vllm_generation.py, andtrl/trainer/grpo_trainer.pyto reflect the actual behavior introduced in #5107 .A regression test update in
tests/test_vllm_client_server.pycoversgenerate(..., logprobs=None)andchat(..., logprobs=None).