vLLM through 0.29.0 Denial of Service via Unbounded P2P KV Offloading Sessions

Advisories

vLLM through 0.29.0 Denial of Service via Unbounded P2P KV Offloading Sessions

severity: high
date: 9/21/2026
Affecting: vllm <= 0.29.0
CVE: CVE-2026-94624
CWE: CWE-770 Allocation of Resources Without Limits or Throttling
CVSS: 8.7
CVSS V4 Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
References: 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
Credit: Mingkai Yu, Jiapeng Li, Jiajia Liu
Description: 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.

Ready to get Started?

Explore VulnCheck, a next-generation Cyber Threat Intelligence platform, which provides exploit and vulnerability intelligence to help you prioritize and remediate vulnerabilities that matter.

Vulnerability Prioritization
Prioritize vulnerabilities that matter based on the threat landscape and defer vulnerabilities that don't.
Early Warning System
Real-time alerting of changes in the vulnerability landscape so that you can take action before the attacks start.

Schedule a Demo