CVE-2026-94624 PUBLISHED

vLLM through 0.29.0 contains a denial of service vulnerability in P2P KV offloading when OffloadingConnector is configured with TieringOffloadingSpec and a peer-to-peer secondary tier. Attackers can supply arbitrary remote host and port values in kv_transfer_params to create unreachable peer sessions that retain ZeroMQ sockets until the context quota is exhausted, causing an uncaught ZMQError that crashes EngineCore and stops all inference.

• Mingkai Yu finder
• Jiapeng Li finder
• Jiajia Liu finder

• Pull Request #51504
• https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/control/zmq.py#L240-L260
• https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/manager.py#L667-L677
• https://github.com/vllm-project/vllm
• VulnCheck Advisory: vLLM through 0.29.0 Denial of Service via Unbounded P2P KV Offloading Sessions

• Allocation of Resources Without Limits or Throttling CWE