---
id: CVE-2026-105757
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, structured-output request failures can escape request-scoped
  validation and reach the EngineCore fatal-error path. A per-request backend
  mismatch can re-…
severity: medium
cvss: 6.5
cvssVector: 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H'
cwe:
  - CWE-20
  - CWE-248
  - CWE-755
vendor: vllm
product: vllm
affected:
  - vllm < 0.30.0
patched:
  - vllm 0.30.0
published: '2026-10-05'
updated: '2026-10-08'
sourceUpdated: '2026-10-08T01:28:00.630'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-105757'
references:
  - url: >-
      https://github.com/vllm-project/vllm/commit/c55e15a44ec4127832d4a86928a356fdd9e68dbd
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/pull/51450'
    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-85xf-c7hm-whqw
    label: security-advisories@github.com
  - url: 'https://github.com/advisories/GHSA-85xf-c7hm-whqw'
  - url: 'https://github.com/vllm-project/vllm'
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-105757.json
  - url: 'https://access.redhat.com/security/cve/CVE-2026-105757'
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2546185'
  - url: 'https://www.cve.org/CVERecord?id=CVE-2026-105757'
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-105757'
tags:
  - nvd
  - cve.org
  - ghsa
  - pip
  - osv
  - csaf
  - vex
  - red-hat
epss: 0.00314
epssPercentile: 0.24131
aliases:
  - GHSA-85xf-c7hm-whqw
  - PYSEC-2026-4199
ecosystem: pip
ssvc:
  exploitation: none
  automatable: 'no'
  technicalImpact: partial
  timestamp: '2026-10-06T13:20:12.110559Z'
ingestedAt: '2026-10-05T23:36:21.157Z'
---

## Overview

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-raise a grammar compilation exception, padding produced by the ngram_gpu speculative-decoding mode can pass a negative token to guidance validation, and the Rust frontend can admit empty structured-output values that the Python frontend rejects, allowing ordinary constrained-generation requests to terminate the shared engine. This issue is fixed in version 0.30.0.

## Affected

- `vllm < 0.30.0`

## Remediation

Upgrade past the affected range:

- `vllm 0.30.0`

## Package advisory (CVE-2026-105757)

Affected packages:

- `vllm < 0.30.0`

Patched in:

- `vllm 0.30.0`

Source: https://github.com/advisories/GHSA-85xf-c7hm-whqw

## Vendor advisories

- **Red Hat VEX** · Moderate · 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 2026-10-06 · [vex](https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-105757.json)