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.
Problem types
CWE-131: Incorrect Calculation of Buffer Size
CWE-704: Incorrect Type Conversion or Cast
Product status
References
github.com/...t/vllm/security/advisories/GHSA-83vm-p52w-f9pw
github.com/vllm-project/vllm/pull/38610
github.com/...t/vllm/security/advisories/GHSA-83vm-p52w-f9pw
github.com/vllm-project/vllm/pull/38610