---
id: CVE-2026-73556
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
  0.26.0, the structured_outputs.regex parameter in
  vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to
  lmformatenforcer.RegexParser without compi…
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'
cwe:
  - CWE-400
  - CWE-1333
vendor: vllm
product: vllm
affected:
  - vllm < 0.26.0
patched:
  - vllm 0.26.0
published: '2026-08-13'
updated: '2026-09-09'
sourceUpdated: '2026-09-09T20:58:37.713'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-73556'
references:
  - url: >-
      https://github.com/vllm-project/vllm/commit/c9a788eedc412acceaa5112e0d44624b49841577
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/pull/47595'
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/releases/tag/v0.26.0'
    label: security-advisories@github.com
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-48jh-3gj7-fg8v
    label: security-advisories@github.com
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-48jh-3gj7-fg8v
    label: 134c704f-9b21-4f2e-91b3-4a467353bcc0
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-73556'
  - url: 'https://github.com/advisories/GHSA-48jh-3gj7-fg8v'
  - url: 'https://github.com/vllm-project/vllm'
  - url: 'https://pypi.org/project/vllm'
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-73556.json
  - url: 'https://access.redhat.com/security/cve/CVE-2026-73556'
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2515404'
  - url: 'https://www.cve.org/CVERecord?id=CVE-2026-73556'
  - url: 'https://access.redhat.com/errata/RHSA-2026:68699'
  - url: 'https://access.redhat.com/errata/RHSA-2026:69466'
  - url: 'https://access.redhat.com/errata/RHSA-2026:69467'
  - url: 'https://access.redhat.com/errata/RHSA-2026:69469'
  - url: 'https://access.redhat.com/errata/RHSA-2026:69464'
  - url: 'https://access.redhat.com/errata/RHSA-2026:70965'
  - url: 'https://access.redhat.com/errata/RHSA-2026:70979'
  - url: 'https://access.redhat.com/errata/RHSA-2026:70995'
  - url: 'https://access.redhat.com/errata/RHSA-2026:70969'
tags:
  - nvd
  - ghsa
  - pip
  - osv
  - csaf
  - vex
  - red-hat
  - score-dispute
epss: 0.00524
epssPercentile: 0.41909
aliases:
  - GHSA-48jh-3gj7-fg8v
  - PYSEC-2026-3933
ecosystem: pip
ingestedAt: '2026-09-04T22:28:54.906Z'
scores:
  nvd: 5.3
  vendor: 7.5
---

## Overview

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in validate_structured_output_request_lm_format_enforcer, allowing an unauthenticated /v1/completions request against the lm-format-enforcer backend to consume a CPU core and stall the structured-output engine path with a catastrophic regular expression. This issue is fixed in version 0.26.0.

## Remediation

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

## Package advisory (CVE-2026-73556)

Affected packages:

- `vllm < 0.26.0`

Patched in:

- `vllm 0.26.0`

Source: https://github.com/advisories/GHSA-48jh-3gj7-fg8v

## 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 2026-09-24 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-73556.json)
- **RHSA-2026:68699** · Red Hat · fixed in: Red Hat AI Inference Server 3.3 · released 2026-09-17 · [advisory](https://access.redhat.com/errata/RHSA-2026:68699)
- **RHSA-2026:69466** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-21 · [advisory](https://access.redhat.com/errata/RHSA-2026:69466)
- **RHSA-2026:69467** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-21 · [advisory](https://access.redhat.com/errata/RHSA-2026:69467)
- **RHSA-2026:69469** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-21 · [advisory](https://access.redhat.com/errata/RHSA-2026:69469)
- **RHSA-2026:69464** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-21 · [advisory](https://access.redhat.com/errata/RHSA-2026:69464)
- **RHSA-2026:70965** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-23 · [advisory](https://access.redhat.com/errata/RHSA-2026:70965)
- **RHSA-2026:70979** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-23 · [advisory](https://access.redhat.com/errata/RHSA-2026:70979)
- **RHSA-2026:70995** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-23 · [advisory](https://access.redhat.com/errata/RHSA-2026:70995)
- **RHSA-2026:70969** · Red Hat · fixed in: Red Hat AI Inference Server 3.4 · released 2026-09-23 · [advisory](https://access.redhat.com/errata/RHSA-2026:70969)