fix: Strip top_logprobs=null before forwarding to vLLM (#609)#1013
Open
cwing-nvidia wants to merge 1 commit intomainfrom
Open
fix: Strip top_logprobs=null before forwarding to vLLM (#609)#1013cwing-nvidia wants to merge 1 commit intomainfrom
cwing-nvidia wants to merge 1 commit intomainfrom
Conversation
Rollout JSONL files serialized by ng_collect_rollouts include explicit top_logprobs: null, which vLLM interprets differently from omitting the field. With logprobs=True and top_logprobs=null, vLLM does not return logprobs content, causing a TypeError crash in chat_completions. Signed-off-by: Chris Wing <cwing@nvidia.com> Made-with: Cursor
damon-mosk-aoyama-nvidia
approved these changes
Apr 6, 2026
1 task
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Rollout JSONL files serialized by ng_collect_rollouts include explicit top_logprobs: null, which vLLM interprets differently from omitting the field. With logprobs=True and top_logprobs=null, vLLM does not return logprobs content, causing a TypeError crash in chat_completions.