CVE-2025-46560

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.

Weakness classification

• security-advisories@github.com: CWE-1333

Primary references

• security-advisories@github.com — Product
• security-advisories@github.com — Exploit, Vendor Advisory
• 134c704f-9b21-4f2e-91b3-4a467353bcc0 — Exploit, Vendor Advisory