Перейти к содержимому
CodeAuditAgent

CVE-2026-54235

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.

СреднийCWE-1287 Все CVE

Слабость

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.

Затронутые продукты

  • vllm vllm

Источники

Найдите уязвимость раньше атакующего.

Войдите через GitHub и запустите первый аудит меньше чем за минуту. Для бесплатного тарифа банковская карта не нужна.