Resource exhaustion in Vllm
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
EPSS: 0.004 (36.5th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 36th percentile — 36.5% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.004 · newest: 0.004 · change: +0.000
Affected products
- Vllm
- Vllm-Project Vllm — versions >= 0.6.4, < 0.12.0
Weakness classification (CWE)
References
- github.com/vllm-project/vllm/security/advisories/GHSA-grg2-63fw-f2qr (Exploit, Vendor Advisory)
Frequently asked questions
- What is CVE-2026-22773?
- CVE-2026-22773 is a medium-severity vulnerability in Vllm, classified under Allocation of Resources Without Limits or Throttling. CVSS score: 6.5/10. Published 2026-01-10.
- How severe is CVE-2026-22773?
- Medium severity. CVSS v3 base score is 6.5 out of 10.