Medium severity6.5NVD Advisory· Published Oct 5, 2026· Updated Oct 8, 2026
CVE-2026-105756
CVE-2026-105756
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected packages
Versions sourced from the GitHub Security Advisory.
| Package | Affected versions | Patched versions |
|---|---|---|
vllmPyPI | < 0.30.0 | 0.30.0 |
Affected products
2Patches
Vulnerability mechanics
References
5- github.com/vllm-project/vllm/commit/e962733e08d10f7ca65dac4df99e116460b8b174nvdPatchWEB
- github.com/vllm-project/vllm/pull/51444nvdIssue TrackingPatchWEB
- github.com/advisories/GHSA-2823-qmq8-rwvjghsaADVISORY
- github.com/vllm-project/vllm/security/advisories/GHSA-2823-qmq8-rwvjnvdMitigationVendor AdvisoryWEB
- github.com/vllm-project/vllm/releases/tag/v0.30.0nvdRelease NotesWEB
News mentions
2- Unpatched Critical LMCache Flaw Lets Unauthenticated Attackers Run Code RemotelyThe Hacker News · Oct 7, 2026
- VLLM: Batch of 11 Medium-Severity Vulnerabilities Disclosed TogetherVypr Intelligence · Oct 6, 2026