Vulnerability Description
vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect shape after the first decode step, causing a RuntimeError that crashes the EngineCore process. The crash is triggered when any request in the batch uses sampling penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). A single request with a penalty parameter (e.g., "repetition_penalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.18.0, < 0.20.0 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/pull/38610Issue TrackingPatch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pwMitigationVendor Advisory
- https://github.com/vllm-project/vllm/pull/38610Issue TrackingPatch
- https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pwMitigationVendor Advisory
FAQ
What is CVE-2026-44223?
CVE-2026-44223 is a vulnerability with a CVSS score of 6.5 (MEDIUM). vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extract_hidden_states speculative decoding proposer in vLLM returns a tensor with an incorrect sha...
How severe is CVE-2026-44223?
CVE-2026-44223 has been rated MEDIUM with a CVSS base score of 6.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-44223?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.