Description
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use Mooncake, unsafe deserialization exposed directly over ZMQ/TCP on all network interfaces will allow attackers to execute remote code on distributed hosts. This is a remote code execution vulnerability impacting any deployments using Mooncake to distribute KV across distributed hosts. This vulnerability is fixed in 0.8.0.
Metrics
CVSS 3.1 9.0/10
CVSS:3.1/AV:A/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:HWeakness enumeration
Affected software
No affected versions have been published.
Timeline
- Published
- Mar 19, 2025
- Last modified
- Jun 17, 2026
- NVD status
- Analyzed