---
id: CVE-2026-94624
title: >-
  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
summary: >-
  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 …
severity: high
cvss: 7.5
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H'
cwe:
  - CWE-770
  - CWE-772
vendor: vllm
product: vllm
affected:
  - vllm <= 0.29.0
published: '2026-09-21'
updated: '2026-09-29'
sourceUpdated: '2026-09-29T12:47:10.597'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-94624'
references:
  - url: 'https://github.com/vllm-project/vllm'
    label: disclosure@vulncheck.com
  - url: >-
      https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/control/zmq.py#L240-L260
    label: disclosure@vulncheck.com
  - url: >-
      https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/kv_offload/tiering/p2p/manager.py#L667-L677
    label: disclosure@vulncheck.com
  - url: 'https://github.com/vllm-project/vllm/pull/51504'
    label: disclosure@vulncheck.com
  - url: >-
      https://www.vulncheck.com/advisories/vllm-through-0.29.0-denial-of-service-via-unbounded-p2p-kv-offloading-sessions
    label: disclosure@vulncheck.com
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-94624.json
  - url: 'https://access.redhat.com/security/cve/CVE-2026-94624'
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2539021'
  - url: 'https://www.cve.org/CVERecord?id=CVE-2026-94624'
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-94624'
  - url: 'https://access.redhat.com/errata/RHSA-2026:84734'
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-frvg-qw88-hww9
  - url: >-
      https://github.com/vllm-project/vllm/commit/93d2cab35e8ae66bbaa1dea1c077986d5a79eb80
  - url: >-
      https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-4006.yaml
  - url: 'https://github.com/vllm-project/vllm/releases/tag/v0.32.0'
  - url: 'https://github.com/advisories/GHSA-frvg-qw88-hww9'
tags:
  - nvd
  - cve.org
  - csaf
  - vex
  - red-hat
  - osv
  - pip
  - ghsa
ssvc:
  exploitation: none
  automatable: 'yes'
  technicalImpact: partial
  timestamp: '2026-09-22T13:26:32.508111Z'
ingestedAt: '2026-09-21T22:54:37.973Z'
epss: 0.00627
epssPercentile: 0.49841
aliases:
  - PYSEC-2026-4006
  - GHSA-frvg-qw88-hww9
ecosystem: pip
patched:
  - vllm 0.30.0
scores:
  nvd: 7.5
  ghsa: 6.5
  osv: 6.5
---

## Overview

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

- `vllm <= 0.29.0`

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.

## Vendor advisories

- **Red Hat VEX** · Important · affected: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · no fix planned: Red Hat AI Inference Server, Red Hat Enterprise Linux AI (RHEL AI) 3, Red Hat OpenShift AI (RHOAI) · updated 2026-10-19 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-94624.json)
- **RHSA-2026:84734** · Red Hat · fixed in: Red Hat OpenShift AI 3.4 · released 2026-10-19 · [advisory](https://access.redhat.com/errata/RHSA-2026:84734)

## Package advisory (CVE-2026-94624)

Affected packages:

- `vllm < 0.30.0`

Patched in:

- `vllm 0.30.0`

Source: https://osv.dev/vulnerability/PYSEC-2026-4006