Upstream information

CVE-2026-44223 at MITRE

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 v3 Scores
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 Bugzilla entry: 1273858 [NEW]

No SUSE Security Announcements cross referenced.


SUSE Timeline for this CVE

CVE page created: Wed Aug 5 15:37:12 2026
CVE page last modified: Wed Aug 5 15:37:12 2026