Vulnerability Description
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.
CVSS Score
MEDIUM
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.8.0, < 0.8.5 |
Related Weaknesses (CWE)
References
- https://github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744fProduct
- https://github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qgExploitVendor Advisory
- https://github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qgExploitVendor Advisory
FAQ
What is CVE-2025-46560?
CVE-2025-46560 is a vulnerability with a CVSS score of 6.5 (MEDIUM). 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 ...
How severe is CVE-2025-46560?
CVE-2025-46560 has been rated MEDIUM with a CVSS base score of 6.5/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2025-46560?
Check the references section above for vendor advisories and patch information. Affected products include: Vllm Vllm.