vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1.
Fix
Patch, vendor advisory and mitigation references on NVD 3
- https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b Patch
- https://github.com/vllm-project/vllm/pull/27204 Issue Tracking, Patch, Vendor Advisory
- https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw Mitigation, Vendor Advisory
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 1
- First seenCVSS 8.3 · vllmNVD modified 2026-10-19 13:10
Affected (CPE criteria) 3
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*cpe:2.3:a:vllm:vllm:0.11.1:rc0:*:*:*:*:*:*cpe:2.3:a:vllm:vllm:0.11.1:rc1:*:*:*:*:*:*
References 4
- https://github.com/vllm-project/vllm/commit/58fab50d82838d5014f4a14d991fdb9352c9c84b Patch
- https://github.com/vllm-project/vllm/pull/27204 Issue Tracking, Patch, Vendor Advisory
- https://github.com/vllm-project/vllm/pull/6613 Issue Tracking
- https://github.com/vllm-project/vllm/security/advisories/GHSA-pmqf-x6x8-p7qw Mitigation, Vendor Advisory