Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [Feature]: Interrupt Reasoning on Pattern [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
vllm-project/vllm#42487•Fetched 2026-05-14 03:29:47
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Author
timbmgtimbmg
Participants
timbmgtimbmg
Timeline (top)
labeled ×1

Root Cause

Currently, vLLM support a thinking budget by token count. It would be great to extend this to match a pattern. For example, whenever the model emits "✅" or ". Done." I would like to interrupt the thinking, because afterwards often comes just self-confirmation and re-checks that don't really alter the final output. I think it would be ideal if some regex could be defined that is checked against the reasoning trace and if it hits the reasoning is interrupted with the reasoning_end_str.

RAW_BUFFERClick to expand / collapse

🚀 The feature, motivation and pitch

Some models are overly verbose in their thinking (Looking at you Qwen3.5/3.6).

Currently, vLLM support a thinking budget by token count. It would be great to extend this to match a pattern. For example, whenever the model emits "✅" or ". Done." I would like to interrupt the thinking, because afterwards often comes just self-confirmation and re-checks that don't really alter the final output. I think it would be ideal if some regex could be defined that is checked against the reasoning trace and if it hits the reasoning is interrupted with the reasoning_end_str.

Alternatives

No response

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

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…
#model download#tokenizer error#prompt formatting#chain error#conversation history

Still need to ship something?

×6

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

Back to top recommendations

TRENDING

vllm - 💡(How to fix) Fix [Feature]: Interrupt Reasoning on Pattern [1 participants]