CVE-2025-46560
HIGH EPSS 34.2%
Published Apr 30, 20251y ago · Modified Jun 17, 20262w ago
7.5 CVSS 3.1
Published Apr 30, 2025 1y ago
Last Modified Jun 17, 2026 2w ago
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 Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H Attack Vector Network
Attack Complexity Low
Privileges Required None
User Interaction None
Scope Unchanged
Confidentiality None
Integrity None
Availability High
Threat Intelligence
EPSS Exploit Probability
34.2% percentile
Exploit & Patch Status
Public Exploit Known
No Patch Available
Weaknesses 1
CWE-1333
Affected Products 1
| Vendor | Product | Version | Range |
|---|---|---|---|
| vllm | vllm | * | ≥0.8.0 – <0.8.5 |
References 2
- github.com https://github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744f4e/vllm/model_executor/models/phi4mm.py#L1182-L1197
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qg
Remediation
No remediation data recorded yet
Check vendor advisories and the NVD entry for patch availability.