Skip to content
LLMHigh

CVE-2026-47155: vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, vLLM's re…

Occurred
Jun 22, 2026
Published
Jun 22, 2026
Source
NVD CVE

Summary

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, vLLM's revision pinning controls do not consistently apply to all artifacts loaded for a model. A deployment that supplies --revision or --code-revision can still load dynamic code, GGUF files, image processors, retrieval side weights, or same-repository subfolder weights/config from an unpinned/default revision. This is a supply-chain integrity issue for pinned vLLM deployments. Operators can believe they are serving a reviewed model revision while vLLM resolves behavior-affecting nested or sibling artifacts outside that reviewed revision. This vulnerability is fixed in 0.22.0.

Tags

  • CVE
  • CVE-2026-47155
  • cvss:MEDIUM

Classification

Category confidence: 90%
Severity confidence: 85%

Rationale: CVE describes a supply-chain integrity vulnerability in vLLM LLM serving engine allowing unpinned artifacts to be loaded, posing security risks.

Classifier: Qwen/Qwen3.5-35B-A3B-FP8

Visit source