CVE-2026-105754 — vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generat…
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data fie…
CVSS 6.5