AUGUST 27, 2026
Live Feed
Back to database
Case File

CVE-2026-53923

HIGH · CVSS 7.5 EPSS 0.28% Public Exploit

Source: NVD + CISA KEV + EPSS (historical backfill) · Published 2026-06-22 · Last synced 2026-08-04

CyberRota Analysis

This is a high severity vulnerability with a CVSS score of 7.5. Public exploit code or proof-of-concept references have been detected in its references.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-53923
Severity
HIGH
CVSS
7.5
EPSS
0.28%

Original NVD 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.

Related CVEs

Other vulnerabilities affecting the same vendor(s)