CVSS 3.1
7.5 highCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:HCVE-2026-22773
High (7.5) in vllm vllm. EPSS 0.4% chance of exploitation in the next 30 days. Fixed in vllm 0.12.0.
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
- EPSS
- 0.4% chance of exploitation in the next 30 days; higher than 38% of CVEs (scores of 2026-10-31)
- CWE
- CWE-770
- Published
- Modified
- Record from
- the NVD, synced
Affected
- vllm:vllm
Packages (OSV)
| Advisory | Ecosystem | Package | Affected | Fixed in |
|---|---|---|---|---|
| GHSA-grg2-63fw-f2qr | PyPI | vllm | >=0.6.4 <0.12.0 | 0.12.0 |
| PYSEC-2026-143 | PyPI | vllm | >=0.6.4 <0.12.0 | 0.12.0 |