litellm - 💡(How to fix) Fix [Bug]: reasoning with recent vllm backends does not work [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
BerriAI/litellm#26501Fetched 2026-04-26 05:06:37
View on GitHub
Comments
0
Participants
1
Timeline
2
Reactions
0
Author
Participants
Timeline (top)
labeled ×2
RAW_BUFFERClick to expand / collapse

Check for existing issues

  • I have searched the existing issues and checked that my issue is not a duplicate.

What happened?

VLLM returns the reasoning tag instead of the (deprecated)reasoning_content. It seems that LiteLLM does not understand and in streaming mode, reasoning is not parsed and returned.

Steps to Reproduce

  1. Run litellm against vllm (0.19.0) provider.
  2. Use model with reasoning.
  3. Reasoning is stripped in streamed responses.

Relevant log output

What part of LiteLLM is this about?

Proxy

What LiteLLM version are you on ?

v1.81.12, but I believe, this is present also in main.

Twitter / LinkedIn details

No response

extent analysis

TL;DR

Update the LiteLLM version or modify the model to not rely on the deprecated reasoning_content tag, as VLLM now returns the reasoning tag instead.

Guidance

  • Verify that the issue persists with the latest version of LiteLLM, as the problem may have been addressed in a more recent release.
  • Check the documentation for VLLM (0.19.0) to ensure that the reasoning tag is correctly handled in streaming mode.
  • Consider modifying the model to use the new reasoning tag instead of the deprecated reasoning_content tag.
  • Test the model with a different provider to determine if the issue is specific to VLLM.

Notes

The issue may be specific to the combination of LiteLLM (v1.81.12) and VLLM (0.19.0), and updating either component may resolve the problem.

Recommendation

Apply workaround: Modify the model to use the new reasoning tag, as updating to a fixed version is not explicitly mentioned in the issue.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING