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
- Vllm
- Vllm-Project Vllm — versions >= 0.8.0, < 0.8.5
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.