PT-2026-2260
CVE-2026-22773
·
Published
2026-01-10
·
Updated
2026-01-13
Description by
CVSS 3.1
7.5
HighMetricsAV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Name of the Vulnerable Software and Affected Versions
vLLM versions 0.6.4 through 0.11.9
Description
vLLM is an inference and serving engine for large language models (LLMs). Users can cause the vLLM engine to crash when serving multimodal models that utilize the Idefics3 vision model implementation. This is achieved by submitting a specifically designed 1x1 pixel image. The crafted image triggers a tensor dimension mismatch, resulting in an unhandled runtime error and complete server termination.
Recommendations
Update to version 0.12.0 or later.
Exploitability
Exploit
Fix
Impacts
Vendors
Affected products
Found an issue in the description? Have something to add? Feel free to write us 👾