6.5

CVE-2026-44223

vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters

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.
Daten sind bereitgestellt durch National Vulnerability Database (NVD)
Vllm ≫ Vllm Version >= 0.18.0 < 0.20.0
VulnDex Vulnerability Enrichment
Diese Information steht angemeldeten Benutzern zur Verfügung. Login Login
Zu dieser CVE wurde keine Warnung gefunden.
EPSS Metriken
Typ Quelle Score Percentile
EPSS FIRST.org 0.37% 0.283
CVSS Metriken
Quelle Base Score Exploit Score Impact Score Vector String
security-advisories@github.com 6.5 2.8 3.6
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
CWE-131 Incorrect Calculation of Buffer Size

The product does not correctly calculate the size to be used when allocating a buffer, which could lead to a buffer overflow.

CWE-704 Incorrect Type Conversion or Cast

The product does not correctly convert an object, resource, or structure from one type to a different type.

https://github.com/vllm-project/vllm/security/advisories/GHSA-83vm-p52w-f9pw
Vendor Advisory
Mitigation
https://github.com/vllm-project/vllm/pull/38610
Patch
Issue Tracking