- CVSS
- MEDIUM · 6.5 v3.1 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Published
- 2026-05-12
- Weakness
- CWE-131, CWE-704
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-44223
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.
References
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-44223 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.