Vulnerability Details CVE-2026-44223
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.
Exploit prediction scoring system (EPSS) score
EPSS Score 0.0
EPSS Ranking 3.4%
CVSS Severity
CVSS v3 Score 6.5
References
Products affected by CVE-2026-44223
-
cpe:2.3:a:vllm:vllm:0.18.0
-
cpe:2.3:a:vllm:vllm:0.18.1
-
cpe:2.3:a:vllm:vllm:0.18.2
-
cpe:2.3:a:vllm:vllm:0.19.0
-
cpe:2.3:a:vllm:vllm:0.19.1
-
cpe:2.3:a:vllm:vllm:0.19.2