transformers - 💡(How to fix) Fix Can not deploy SFT Qwen3.5-9B model [13 comments, 7 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
huggingface/transformers#44541Fetched 2026-04-08 00:27:48
View on GitHub
Comments
13
Participants
7
Timeline
24
Reactions
5
Author
Timeline (top)
commented ×13subscribed ×6mentioned ×4labeled ×1
RAW_BUFFERClick to expand / collapse

System Info

I SFT Qwen3.5-9B model with transformers==5.2.0

Reproduction

When I try to deploy my model with vllm==0.17.0, it reports:

TypeError: Invalid type of HuggingFace config. Expected type: <class 'vllm.transformers_utils.configs.qwen3_5.Qwen3_5Config'>, but found type: <class 'transformers.models.qwen3_5.configuration_qwen3_5.Qwen3_5TextConfig'>

I wonder how can I fix it.

Expected behavior

vllm==0.17.0 requires transformers<5, but transformers>5 is required to support Qwen3.5, kind of strange.

extent analysis

Fix Plan

Downgrade transformers to a compatible version

To resolve the issue, we need to downgrade the transformers library to a version that is compatible with vllm==0.17.0.

Steps:

  1. Check the compatible version: Look for the minimum required transformers version in the vllm==0.17.0 documentation or source code.
  2. Downgrade transformers: Run the following command in your terminal or command prompt:

pip install transformers==4.25.1

   Replace `4.25.1` with the compatible version you found in step 1.
3. **Verify the downgrade**: Run `pip freeze` to check if the transformers version has been downgraded correctly.

#### Example Code

No code changes are required in this case. The fix involves downgrading a library, which can be done using pip.

#### Verification

To verify that the fix worked, try deploying your model with vllm==0.17.0 again. If the error is resolved, you should be able to deploy your model successfully.

#### Extra Tips

* Always check the documentation or source code of the library you're using to find the minimum required version.
* Be cautious when downgrading libraries, as it may break other dependencies or features in your project.
* Consider pinning your dependencies to specific versions in your `requirements.txt` file to avoid similar issues in the future.

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…

FAQ

Expected behavior

vllm==0.17.0 requires transformers<5, but transformers>5 is required to support Qwen3.5, kind of strange.

Still need to ship something?

×6

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

Back to top recommendations

TRENDING