CVE-2025-46560

Summary

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.

Affected Software

Weaknesses

• CWE-1333: CWE-1333: Inefficient Regular Expression Complexity

ADP Enrichment

CISA ADP Vulnrichment

• SSVC:
• Exploitation: poc
  • Automatable: no
  • Technical Impact: partial

Additional References

• https://github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qg

References

• https://github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qg
• https://github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744f4e/vllm/model_executor/models/phi4mm.py#L1182-L1197

• ←Previous
• Next→