---
id: GHSA-8qpc-6rxx-4pxf
title: 'Duplicate Advisory: vllm p2p never connected zmq_exhaustion'
summary: 'Duplicate Advisory: vllm p2p never connected zmq_exhaustion'
severity: high
cvss: 7.5
cwe:
  - CWE-770
vendor: vllm
product: vllm
ecosystem: pip
affected:
  - 'vllm >= 0, < 0.30.0'
patched:
  - vllm 0.30.0
published: '2026-09-22'
updated: '2026-10-27'
sourceUpdated: '2026-10-27T14:45:48Z'
source: GHSA
sourceUrl: 'https://github.com/advisories/GHSA-8qpc-6rxx-4pxf'
references:
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-94624'
  - url: 'https://github.com/vllm-project/vllm/pull/51504'
  - url: 'https://github.com/vllm-project/vllm'
  - url: >-
      https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/control/zmq.py#L240-L260
  - url: >-
      https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/manager.py#L667-L677
  - url: >-
      https://www.vulncheck.com/advisories/vllm-through-0.29.0-denial-of-service-via-unbounded-p2p-kv-offloading-sessions
  - url: >-
      https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-4006.yaml
  - url: 'https://github.com/advisories/GHSA-8qpc-6rxx-4pxf'
tags:
  - ghsa
  - pip
ingestedAt: '2026-10-27T16:11:58.748Z'
---

## Overview

## Duplicate Advisory

This advisory has been withdrawn because it is a duplicate of GHSA-frvg-qw88-hww9. This link is maintained to preserve external references.

## Original 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

- `vllm >= 0, < 0.30.0`

## Remediation

Upgrade to a patched release:

- `vllm 0.30.0`