vllm
Affected
- introduced
0.6.4, fixed0.12.0(ecosystem)
Fixed versions
0.12.0
Fix
- Fixed version
0.12.0pip install --upgrade vllm==0.12.0
Advisory
Also known as: CVE-2026-22773, GHSA-grg2-63fw-f2qr
The record has no summary.
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.
High Basis: CVSS v3 score 7.5, vector CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
0.6.4, fixed 0.12.0 (ecosystem)0.12.0
0.12.0pip install --upgrade vllm==0.12.0Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0