---
id: CVE-2026-105756
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, OpenAI-compatible request models accept a non-empty cache_salt value
  without enforcing the character and length restrictions required by the
  IPCCacheServ…
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
vendor: vllm
product: vllm
affected:
  - vllm < 0.30.0
patched:
  - vllm 0.30.0
published: '2026-10-05'
updated: '2026-10-08'
sourceUpdated: '2026-10-08T01:28:23.010'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-105756'
references:
  - url: >-
      https://github.com/vllm-project/vllm/commit/e962733e08d10f7ca65dac4df99e116460b8b174
    label: security-advisories@github.com
  - url: 'https://github.com/vllm-project/vllm/pull/51444'
    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-2823-qmq8-rwvj
    label: security-advisories@github.com
  - url: 'https://github.com/advisories/GHSA-2823-qmq8-rwvj'
  - url: 'https://github.com/vllm-project/vllm'
  - url: >-
      https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-105756.json
  - url: 'https://access.redhat.com/security/cve/CVE-2026-105756'
  - url: 'https://bugzilla.redhat.com/show_bug.cgi?id=2546182'
  - url: 'https://www.cve.org/CVERecord?id=CVE-2026-105756'
  - url: 'https://nvd.nist.gov/vuln/detail/CVE-2026-105756'
  - url: 'https://pypi.org/project/vllm'
tags:
  - nvd
  - cve.org
  - ghsa
  - pip
  - osv
  - csaf
  - vex
  - red-hat
epss: 0.00332
epssPercentile: 0.26204
aliases:
  - GHSA-2823-qmq8-rwvj
  - PYSEC-2026-4306
ecosystem: pip
ssvc:
  exploitation: none
  automatable: 'no'
  technicalImpact: partial
  timestamp: '2026-10-06T14:41:36.857213Z'
ingestedAt: '2026-10-05T23:36:21.156Z'
---

## Overview

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent users. 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-2026-105756)

Affected packages:

- `vllm < 0.30.0`

Patched in:

- `vllm 0.30.0`

Source: https://github.com/advisories/GHSA-2823-qmq8-rwvj

## 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-2026-105756.json)