CVE-2025-29783 — vLLM Allows Remote Code Execution via Mooncake Integration
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/T…
Published: 2025-03-19 · CVSS: 9.1 · CVSS 3.1
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.
Source: CVE Program · Revision 8b16575c39f1e1810c5e863010da073d2d3285e7