Vulnerability · Published Sep 21, 2026 · Assigned by VulnCheck

CVE-2026-94624vLLM through 0.29.0 Denial of Service via Unbounded P2P KV Offloading Sessions

High 7.5

In plain English

A high-severity resource allocation without limits in vllm from vllm-project. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 38% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)7.5High

Exploit odds (30 days)0.4%top 62.2% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	vllm	0.32.0	GHSA-frvg-qw88-hww9
PyPI	vllm	0.30.0	PYSEC-2026-4006

Affected products (as reported)

Vendor	Product	Versions
vllm-project	vllm	0 – through 0.29.0

Weakness: CWE-770 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

References

Pull Request #51504 issue-tracking, patch
https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/control/zmq.py#L240-L260 technical-description
https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/manager.py#L667-L677 technical-description
https://github.com/vllm-project/vllm product
VulnCheck Advisory: vLLM through 0.29.0 Denial of Service via Unbounded P2P KV Offloading Sessions third-party-advisory