CVE-2026-69147: vLLM is an inference and serving engine for large language models. Prior to 0.28.0, request bodies for Chat Completions

vLLM, a system that runs large language models, had a vulnerability before version 0.28.0 where attackers could request video processing using a specific decoder (PyNvVideoCodec) that wasn't properly accounted for in GPU memory budgets. This could cause the shared GPU memory to fill up, leading to crashed requests, crashed worker processes, or denial of service (making the system unavailable).