CVE-2026-105756
vLLM is an inference and serving engine for large language models.
Does this matter?
Lower severity and a low EPSS score (0.33%). Track it; it rarely justifies an emergency change on its own.
Description
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.
- CVSS 3.1
- 6.5 MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- EPSS
- 0.33% probability · 26th percentile
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-20, CWE-248
- Affected
- vllm/vllm
- Source
- security-advisories@github.com
EPSS moved from 0.3% on 6 October 2026 to 0.3% on 26 October 2026.
References
- https://github.com/vllm-project/vllm/commit/e962733e08d10f7ca65dac4df99e116460b8b174Patch
- https://github.com/vllm-project/vllm/pull/51444Issue Tracking, Patch
- https://github.com/vllm-project/vllm/releases/tag/v0.30.0Release Notes
- https://github.com/vllm-project/vllm/security/advisories/GHSA-2823-qmq8-rwvjMitigation, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.