Disclosure 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 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.
Source-reported weakness categories
CWE-20, CWE-248
Source-specific records & product guidance
Sources retain their own attribution and scoring. Follow the original record to confirm affected versions, fixed releases, and configuration conditions.
NIST National Vulnerability Database · NVD-CVE-2026-105756
Open original source · Updated Oct 06, 2026
Only CPE matches marked vulnerable=true are indexed. AND/OR platform conditions must be checked in the original NVD record.
GitHub Reviewed Security Advisories · GHSA-2823-qmq8-rwvj
Open original source · Updated Oct 05, 2026
vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service
Source severity: MEDIUM / 0
| Ecosystem | Package | Affected range | First patched |
|---|---|---|---|
| pip | vllm | < 0.30.0 | 0.30.0 |
Original records & references
PUBLISHED 2026-10-05T19:17:02-04:00
MODIFIED 2026-10-06T11:17:15-04:00
INGESTED 2026-10-06T11:45:40-04:00