CVE-2026-44223: Vllm

Medium severity, CVSS 6.5. EPSS: 0.4% chance of exploitation in the next 30 days.

vLLM is an inference and serving engine for large language models (LLMs). From 0.18.0 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.

Affected products

• Vllm Vllm: from 0.18.0, before 0.20.0 (fixed in 0.20.0)

Published 2026-05-12. Last modified 2026-06-22.