CVE-2025-46560: vLLM: Quadratic Time Complexity in Input Token Processing leads to denial of service
(updated )
A critical performance vulnerability has been identified 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.
References
- github.com/advisories/GHSA-vc6m-hm49-g9qg
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2022.yaml
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744f4e/vllm/model_executor/models/phi4mm.py
- github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qg
- nvd.nist.gov/vuln/detail/CVE-2025-46560
- pypi.org/project/vllm
Code Behaviors & Features
Detect and mitigate CVE-2025-46560 with GitLab Dependency Scanning
Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →