vllm package vulnerabilities
Advisories affecting the vllm package. A list cannot tell you whether your installed version is affected — the dependency check can.
10 vulnerabilities tracked.
Check which version you are running → — this page lists advisories for the package; only a version check can tell you whether you are affected.
- 9.8 vLLM is an inference and serving engine for large language models.
- 8.8 vLLM is an inference and serving engine for large language models.
- 8.1 vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution
- 6.5 vllm p2p never connected zmq_exhaustion
- 6.5 vLLM is an inference and serving engine for large language models.
- 6.5 vLLM is an inference and serving engine for large language models.
- 6.5 vLLM is an inference and serving engine for large language models.
- 6.5 vLLM is an inference and serving engine for large language models.
- 6.5 vLLM is an inference and serving engine for large language models.
- 4.7 vLLM is an inference and serving engine for large language models.
What this covers
This feed accumulates forward from the day it started storing records, and a name search that finds nothing here is also looked up against the registers directly — so an older advisory resolves even when it predates the corpus. It is still a reading view, not a substitute for the vendor's own advisory, and absence from this page is not a statement that vllm is free of vulnerabilities.
Query this from an agent over MCP · Check a lockfile by version
Other packages tracked here
filelock node-forge github.com/labstack/echo/v4 github.com/labstack/echo/v5 undici virtualenv adminneo-org/adminneo @highcharts/dashboards authlib pypdf highcharts GitPython seroval zip org.mariadb.jdbc:mariadb-java-client @highcharts/grid-pro org.keycloak:keycloak-services phpoffice/phpspreadsheet mlflow rustls russh crass pyasn1 onnx