Issue Station
Sign In
Tools hereToolbox

vllm - 💡(How to fix) Fix [Usage]: port question [6 comments, 2 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#38820•Fetched 2026-04-08 02:34:41
View on GitHub
Comments
6
Participants
2
Timeline
7
Reactions
0
Author
CertainlyGoCertainlyGo
Participants
Alex-ai-futureAlex-ai-futureCertainlyGoCertainlyGo
Timeline (top)
commented ×6labeled ×1

Code Example

The output of `python collect_env.py`
RAW_BUFFERClick to expand / collapse

Your current environment

The output of `python collect_env.py`

I'm unable to access the port when running inference on Qwen3.5-9B with vLLM v0.18. It hangs without throwing any errors, but switching to v0.17 works fine.

curl http://127.0.0.1:8000/v1/models curl: (7) Failed to connect to 127.0.0.1 port 8000 after 1 ms: Couldn't connect to server

(APIServer pid=6112) INFO: Started server process [6112] (APIServer pid=6112) INFO: Waiting for application startup. (APIServer pid=6112) INFO: Application startup complete.

How would you like to use vllm

I want to run inference of a qwen3.5-9b. I don't know how to integrate it with vllm.

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.

extent analysis

TL;DR

Downgrade to vLLM v0.17 as a temporary workaround to resolve the connection issue with Qwen3.5-9B.

Guidance

  • The issue seems to be specific to vLLM v0.18, as switching to v0.17 resolves the problem, indicating a potential version-specific bug.
  • Verify that the server is correctly configured and running by checking the logs for any error messages or startup issues.
  • Try to isolate the problem by testing other models or versions to see if the issue is specific to Qwen3.5-9B and v0.18.
  • Check the documentation and release notes for v0.18 to see if there are any known issues or changes that could be causing the problem.

Notes

The exact cause of the issue is unclear, but downgrading to v0.17 provides a temporary solution. Further investigation is needed to determine the root cause and find a permanent fix.

Recommendation

Apply workaround: Downgrade to v0.17, as it is known to work with Qwen3.5-9B, allowing for temporary continued use while the issue with v0.18 is investigated.

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…
#api#prompt template#agent execution#callback error#memory management

Still need to ship something?

×6

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

Back to top recommendations

TRENDING