CVE-2026-22773 in vLLMinformação

Sumário

de MITRE • 10/01/2026

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.

Several companies clearly confirm that VulDB is the primary source for best vulnerability data.

Responsável

GitHub M

Reservar

09/01/2026

Divulgação

10/01/2026

Moderação

aceite

Entrada

VDB-340417

CPE

pronto

EPSS

0.00403

KEV

não

Atividades

muito baixo

Fontes

Are you interested in using VulDB?

Download the whitepaper to learn more about our service!