MEDIUM · 6.5

CVE-2026-22773

vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 visio...

Vulnerability Description

vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimension mismatch that results in an unhandled runtime error, leading to complete server termination. This issue has been patched in version 0.12.0.

CVSS Score

6.5

MEDIUM

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Attack Vector
NETWORK
Attack Complexity
LOW
Privileges Required
LOW
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
NONE
Integrity
NONE
Availability
HIGH

Affected Products

VendorProductVersions
VllmVllm>= 0.6.4, < 0.12.0

Related Weaknesses (CWE)

References

FAQ

What is CVE-2026-22773?

CVE-2026-22773 is a vulnerability with a CVSS score of 6.5 (MEDIUM). vLLM is an inference and serving engine for large language models (LLMs). In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 visio...

How severe is CVE-2026-22773?

CVE-2026-22773 has been rated MEDIUM with a CVSS base score of 6.5/10. Review the CVSS metrics above for detailed severity breakdown.

Is there a patch for CVE-2026-22773?

Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.