Aller au contenu
en Se connecter
5.3 Moyenne

CVE-2026-53923 vLLM is an inference and serving engine for large language models (LLMs)

Description

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.

Produits et versions touchés

Produit Versions touchées Corrigé en
vllm 0.5 0.5.5 → < 0.23.1rc0 0.23.1rc0

Références

Chronologie

  1. Publiée
  2. Dernière modification

Autres CVE de vllm

Les 121 CVE de vllm →
CVE-2026-115918 vLLM is an inference and serving engine for large language models 6.5 Moyenne CVE-2026-115917 vLLM is an inference and serving engine for large language models 3.4 Faible CVE-2026-115916 vLLM is an inference and serving engine for large language models 6.5 Moyenne CVE-2026-115915 vLLM is an inference and serving engine for large language models 8.1 Élevée
Suivre cette CVE