---
id: CVE-2026-105759
title: vLLM is an inference and serving engine for large language models
summary: >-
  vLLM is an inference and serving engine for large language models. Prior to
  0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP
  method token as a Prometheus label for requests reaching registered routes. An
  una…
severity: medium
cvss: 5.9
cvssVector: 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H'
cwe:
  - CWE-400
vendor: vllm-project
product: vllm
affected:
  - vllm < 0.30.0
published: '2026-10-05'
updated: '2026-10-05'
sourceUpdated: '2026-10-05T23:17:02.760'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-105759'
references:
  - url: >-
      https://github.com/vllm-project/vllm/commit/3735c2d5f5248259482b9045c34fb7a8a3892352
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/pull/56058'
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/releases/tag/v0.30.0'
    label: security-advisories@github.com
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-5fj9-pfhr-6j48
    label: security-advisories@github.com
tags:
  - nvd
  - cve.org
ingestedAt: '2026-10-05T23:36:21.158Z'
---

## Overview

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique arbitrary method tokens to unguarded routes such as /tokenize, causing Prometheus's Family::get_or_create function to permanently create counter and histogram label sets. Those label sets increase process memory usage and enlarge the /metrics response until the service or monitoring path is exhausted. This issue is fixed in version 0.30.0.

## Remediation

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