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.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-502"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/29xxx/CVE-2025-29783.json"
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "0.6.5"
},
{
"fixed": "0.8.0"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "288ca110f68d23909728627d3100e5a8db820aa2"
}
],
"source": "REFERENCES_COMMIT"
}
]
}