Description
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.
Problem types
CWE-770: Allocation of Resources Without Limits or Throttling
Product status
References
github.com/...t/vllm/security/advisories/GHSA-69j4-grxj-j64p
github.com/vllm-project/vllm/pull/27205
github.com/...ommit/3ada34f9cb4d1af763fdfa3b481862a93eb6bd2b
github.com/...5ed6fe6226997fb/vllm/entrypoints/chat_utils.py
github.com/...97fb/vllm/entrypoints/openai/serving_engine.py
