CVE-2025-46560

HIGH EPSS 34.2%
Published Apr 30, 20251y ago · Modified Jun 17, 20262w ago
7.5 CVSS 3.1
High
Find Similar
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
7.5
Exploitability
3.9
Impact
3.6
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

VendorProductVersionRange
vllmvllm*≥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
    Product
  • github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qg
    ExploitVendor Advisory

Remediation

No remediation data recorded yet

Check vendor advisories and the NVD entry for patch availability.