Upstream information
Description
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.SUSE information
Overall state of this security issue: Does not affect SUSE products
This issue is currently rated as having moderate severity.
| CVSS detail | CNA (GitHub) |
|---|---|
| Base Score | 6.5 |
| Vector | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |
| Attack Vector | Network |
| Attack Complexity | Low |
| Privileges Required | Low |
| User Interaction | None |
| Scope | Unchanged |
| Confidentiality Impact | None |
| Integrity Impact | None |
| Availability Impact | High |
| CVSSv3 Version | 3.1 |
SUSE Timeline for this CVE
CVE page created: Wed Aug 5 15:37:12 2026CVE page last modified: Wed Aug 5 15:37:12 2026