- vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambig... CVE-2026-22773

CVE ID : CVE-2026-22773 Published : Jan. 10, 2026, 7:16 a.m. | 19 minutes ago 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. Severity: 6.5 | MEDIUM Visit the link for more details, such as CVSS details, affected products, timeline, and more...

Source: Telegram CVE Monitor