Перейти к содержимому
CodeAuditAgent

CVE-2026-73558

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0.

СреднийCWE-190 Все CVE

Слабость

vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0.

Источники

Найдите уязвимость раньше атакующего.

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