CVE-2025-46560

See a problem?
Please try reporting it to the source first.
Source
https://cve.org/CVERecord?id=CVE-2025-46560
Import Source
https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2025-46560.json
JSON Data
https://api.osv.dev/v1/vulns/CVE-2025-46560
Aliases
Related
Published
2025-04-30T00:24:53.750Z
Modified
2026-07-07T17:56:27.764573617Z
Severity
  • 6.5 (Medium) CVSS_V3 - CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H CVSS Calculator
Summary
vLLM phi4mm: Quadratic Time Complexity in Input Token Processing​ leads to denial of service
Details

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.

Database specific 
{
    "cwe_ids": [
        "CWE-1333"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/46xxx/CVE-2025-46560.json",
    "cna_assigner": "GitHub_M"
}
References

Affected packages

Git / github.com/vllm-project/vllm

Affected ranges

Type
GIT
Repo
https://github.com/vllm-project/vllm
Events
Introduced
966f933ee1cd7c9a41db60de5c7ff98657005251
Fixed
ba41cc90e8ef7f236347b2f1599eec2cbb9e1f0d

Database specific

source 
"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2025-46560.json"