---
id: CVE-2026-34756
title: vLLM is an inference and serving engine for large language models (LLMs)
summary: >-
  vLLM is an inference and serving engine for large language models (LLMs). From
  0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM
  OpenAI-compatible API server. Due to the lack of an upper bound validation on
  the…
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-770
  - CWE-1284
vendor: vllm
product: vllm
affected:
  - 'vllm >= 0.1.0, < 0.19.0'
patched:
  - vllm 0.19.0
published: '2026-04-06'
updated: '2026-07-07'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-34756'
references:
  - url: >-
      https://github.com/vllm-project/vllm/commit/b111f8a61f100fdca08706f41f29ef3548de7380
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/pull/37952'
    label: security-advisories@github.com
  - url: >-
      https://github.com/vllm-project/vllm/security/advisories/GHSA-3mwp-wvh9-7528
    label: security-advisories@github.com
  - url: 'https://access.redhat.com/errata/RHSA-2026:36005'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/errata/RHSA-2026:36006'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://access.redhat.com/security/cve/CVE-2026-34756'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2455425'
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-34756.json
    label: 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-34756'
  - url: >-
      https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2298.yaml
  - url: 'https://github.com/vllm-project/vllm'
tags:
  - nvd
  - osv
  - pip
epss: 0.00766
epssPercentile: 0.53531
ingestedAt: '2026-07-07T12:52:59.582Z'
aliases:
  - GHSA-3mwp-wvh9-7528
  - PYSEC-2026-2298
ecosystem: pip
---

## Overview

vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.19.0, a Denial of Service vulnerability exists in the vLLM OpenAI-compatible API server. Due to the lack of an upper bound validation on the n parameter in the ChatCompletionRequest and CompletionRequest Pydantic models, an unauthenticated attacker can send a single HTTP request with an astronomically large n value. This completely blocks the Python asyncio event loop and causes immediate Out-Of-Memory crashes by allocating millions of request object copies in the heap before the request even reaches the scheduling queue. This vulnerability is fixed in 0.19.0.

## Affected

- `vllm >= 0.1.0, < 0.19.0`

## Remediation

Upgrade past the affected range:

- `vllm 0.19.0`

## Package advisory (CVE-2026-34756)

Affected packages:

- `vllm >= 0.1.0, < 0.19.0`

Patched in:

- `vllm 0.19.0`

Source: https://osv.dev/vulnerability/GHSA-3mwp-wvh9-7528