---
id: CVE-2026-9540
aliases:
  - GHSA-98f3-hwg4-4rf7
  - PYSEC-2026-3407
title: 'vllm has Improper Resource Shutdown or Release '
summary: 'vllm has Improper Resource Shutdown or Release '
severity: medium
cvss: 5.3
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L'
vendor: vllm
product: vllm
ecosystem: pip
affected:
  - vllm <= 0.19.0
published: '2026-05-26'
updated: '2026-07-13'
source: OSV
sourceUrl: 'https://osv.dev/vulnerability/GHSA-98f3-hwg4-4rf7'
references:
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-9540'
  - url: 'https://github.com/vllm-project/vllm/issues/37343'
  - url: 'https://github.com/vllm-project/vllm/pull/37594'
  - url: 'https://github.com/vllm-project/vllm'
  - url: 'https://ingero.io/debugging-vllm-latency-minimax-ollama-mcp'
  - url: 'https://vuldb.com/submit/814645'
  - url: 'https://vuldb.com/vuln/365601'
  - url: 'https://vuldb.com/vuln/365601/cti'
tags:
  - osv
  - pip
epss: 0.00427
epssPercentile: 0.36612
ingestedAt: '2026-07-13T18:57:55.777Z'
---

## Overview

A vulnerability was identified in vllm-project vllm 0.19.0. This issue affects some unknown processing of the component OpenAI-compatible Serving Path. Such manipulation leads to denial of service. It is possible to launch the attack remotely. The exploit is publicly available and might be used. The pull request to fix this issue awaits acceptance.

## Affected packages

- `vllm <= 0.19.0`

## Remediation

Refer to the advisory for the patched release.