Vulnerability Monitor

The vendors, products, and vulnerabilities you care about

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.


Published

2025-04-30T01:15:52.097

Last Modified

2025-05-28T19:15:56.887

Status

Analyzed

Source

[email protected]

Severity

CVSSv3.1: 6.5 (MEDIUM)

Weaknesses
  • Type: Secondary
    CWE-1333

Affected Vendors & Products
Type Vendor Product Version/Range Vulnerable?
Application vllm vllm < 0.8.5 Yes

References