TI-2025-29807 CVE-2025-47277 · GHSA-hjq4-87xh-g4fv
vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
Priority MEDIUM 51
vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache transfer integration with the V0 engine.