---
cve: "CVE-2026-53923"
severity: "MEDIUM"
cvss: 5.3
epss: "28%"
vendor: "vllm-project"
kev: false
exploited: false
published: "2026-06-22 23:16:30"
tags: [cve, security, medium]
source: tsecurity.de CVE-Dossier
exported: "2026-09-07T07:33:44+02:00"
---

# CVE-2026-53923

> 5.3 MEDIUM · 🧪 PoC

## Beschreibung

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.

## CVSS-Vektor

```
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N
```

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Netzwerk | bad |
| AC Komplexität | Gering | bad |
| PR Privilegien | Keine | bad |

## Patch verfügbar (OSV)

- f219788f91952827132fa4fdf916427cd20d225e (Commit)

## Referenzen

- <https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4>
- <https://github.com/vllm-project/vllm/pull/44971>
- <https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-53923) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_