Lucene search
+L

CVE-2026-53923 vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow

🗓️ 22 Jun 2026 21:55:42Reported by GitHub_MType 
cvelist
 cvelist
🔗 www.cve.org👁 54 Views

Integer truncation in vLLM GGUF kernels causes GPU memory leakage and data disclosure; fixed in 0.23.1rc0.

Related
Affected
Refs
ReporterTitlePublishedViews
Family
attackerkb
ATTACKERKB
CVE-2026-53923
22 Jun 202621:55
attackerkb
cgr
Chainguard
CVE-2026-53923 vulnerabilities
2 Jul 202602:17
cgr
circl
Circl
CVE-2026-53923
23 Jun 202600:15
circl
cve
CVE
CVE-2026-53923
22 Jun 202621:55
cve
euvd
EUVD
EUVD-2026-38400
22 Jun 202621:55
euvd
github
Github Security Blog
vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving
17 Jun 202614:03
github
nvd
NVD
CVE-2026-53923
22 Jun 202623:16
nvd
osv
OSV
CGA-8Q53-Q9V9-JC4M
1 Jul 202619:03
osv
osv
OSV
GHSA-5JV2-G5WQ-CMR4 vLLM: GGUF dequantize kernel int truncation exposes uninitialized GPU memory in multi-tenant serving
17 Jun 202614:03
osv
osv
OSV
MINI-F56M-6PF7-HJ95
30 Jun 202608:11
osv
Rows per page
[
  {
    "vendor": "vllm-project",
    "product": "vllm",
    "versions": [
      {
        "version": ">= 0.5.5, < 0.23.1rc0",
        "status": "affected"
      }
    ]
  }
]

Data

Build on a solid foundation with Vulners data

We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data

Api

Power your application with Vulners API

The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access

App

Assess and manage vulnerabilities with Vulners tools

Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation