vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, the /v1/chat/completions and /tokenize endpoints allow a chat_template_kwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chat_template_kwargs parameters, it is possible to block processing of the API server for long periods of time, delaying all other requests. This issue has been patched in version 0.11.1.

vLLM is an inference and serving engine for large language models (LLM ...

vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

Уязвимость библиотеки для работы с большими языковыми моделями (LLM) vLLM, связанная с неограниченным распределением ресурсов, позволяющая нарушителю вызвать отказ в обслуживании