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 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.
- Affected products
- Vllm
- Vllm
- < 0.12.0
- Fix
- Available
- CVSS 3.1
- 7.5 HIGH
- EPSS
- 0.4% (33th percentile)
- Weakness
- CWE-770
- NVD status
- Analyzed
- Published
- 2026-01-10
CVE-2026-22773 at NVD
No indexed exploits for CVE-2026-22773 yet
Our index is partial: it proves presence, never absence
No exploit for CVE-2026-22773 has been indexed yet. Our index is built from live traffic and upstream syncs, so this page can only say what it knows — not that no exploit exists.