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

What is CVE-2026-22773?

CVE-2026-22773 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 10 Jan 2026. Any signed-in user can exploit it over the network, with no action from the victim.

Official 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.

Weakness: CWE-770

Which versions are affected by CVE-2026-22773?

3 open source packages ship an affected version, including vllm. It affects 1 product.

Products include Vllm Vllm.

How do I fix CVE-2026-22773?

Upgrade vllm to 0.12.0 or later.

Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.

Is CVE-2026-22773 being exploited?

There is no known exploitation of CVE-2026-22773 in the wild and no public exploit code.

Other vulnerabilities in Vllm Vllm

• CVE-2025-32444 vLLM Vulnerable to Remote Code Execution via Mooncake Integration Critical 10.0
• CVE-2026-22778 vLLM leaks a heap address when PIL throws an error Critical 9.8
• CVE-2025-47277 vLLM Allows Remote Code Execution via PyNcclPipe Communication Service Critical 9.8
• CVE-2024-11041 Remote Code Execution in vllm-project/vllm Critical 9.8
• CVE-2026-48746 vLLM: OpenAI auth bypass Critical 9.1

All Vllm Vllm vulnerabilities

Sources

• CVE record
• NVD
• OSV
• GitHub advisory
• How this page is made

Also known as GHSA-grg2-63fw-f2qr, PYSEC-2026-143.