Vulnerability in Vllm

CVE-2025-46560

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to ​​inefficient list concatenation operations​​, the algorithm exhibits ​​quadratic time complexity (O(n²))​​, allowing malicious actors to trigger resource exhaustion via specially crafted inputs. This issue has been patched in version 0.8.5.

Vulnerability class: ReDoS (Regular Expression Denial of Service)

Published · last modified .

CVSS v3 metric

CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.

EPSS exploit prediction

EPSS 0.005, 45.6th percentile (scored ); unchanged over 30 days. About EPSS.

Affected products

Weakness classification (CWE)

Public exploits and proof-of-concept code

Also mentioned in 1 other repository (fkie-cad/nvd-json-data-feeds). These reference the CVE in a list, notes or a scanner and are not exploit code for it.

References