Описание
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors that can crash the inference worker. This vulnerability is fixed in 0.23.1rc0.
Ссылки
- Patch
- Issue Tracking
- ExploitThird Party Advisory
Уязвимые конфигурации
EPSS
6.5 Medium
CVSS3
Дефекты
Связанные уязвимости
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors that can crash the inference worker. This vulnerability is fixed in 0.23.1rc0.
vLLM is an inference and serving engine for large language models (LLM ...
vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
EPSS
6.5 Medium
CVSS3