PYSEC-2026-145

vLLM is an inference and serving engine for large language models (LLMs). From to before 0.20.0, the extracthiddenstates 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 (repetitionpenalty, frequencypenalty, or presencepenalty). A single request with a penalty parameter (e.g., "repetitionpenalty": 1.1) is sufficient to crash the server. This vulnerability is fixed in 0.20.0.