Instituto Nacional de ciberseguridad. Sección Incibe
Instituto Nacional de Ciberseguridad. Sección INCIBE-CERT

CVE-2026-53923

Gravedad CVSS v4.0:
MEDIA
Tipo:
CWE-200 Revelación de información
Fecha de publicación:
22/06/2026
Última modificación:
24/06/2026

Descripción

*** Pendiente de traducción *** vLLM is an inference and serving engine for large language models (LLMs). From 0.5.5 until 0.23.1rc0, integer truncation of tensor dimensions in vLLM's GGUF dequantize kernels (csrc/quantization/gguf/gguf_kernel.cu) causes partial tensor processing. The output tensor is allocated at full size via torch::empty (uninitialized memory), but the dequantize CUDA kernel processes only a truncated number of elements. The unfilled portion of the output tensor retains whatever was previously in GPU memory. In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure. This vulnerability is fixed in 0.23.1rc0.

Productos y versiones vulnerables

CPE Desde Hasta
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* 0.5.5 (incluyendo) 0.23.1 (excluyendo)