CVE-2026-53923
HIGHDescription
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.
How to fix
TridentStack Control can deploy fixes like this automatically across your Windows, macOS, and Linux fleet. See how it works
Remediation is compiled from vendor and distribution security advisories. Always confirm against the linked source for your exact version and platform.
CVSS v3 Vector
Exploitability
Impact
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Exploit Intelligence
Moderate risk: more likely to be exploited than 40% of all known CVEs.
References
Related Vulnerabilities
Other CWE-200 (Information Exposure) vulnerabilities, ordered by exploit likelihood. View all
| CVE | Severity | CVSS | EPSS | Exploited | Fix |
|---|---|---|---|---|---|
| CVE-2024-24919 | High | 8.6 | 100% | KEV + Ransom | - |
| CVE-2020-14181 | Medium | 5.3 | 100% | - | Fix |
| CVE-2021-34429 | Medium | 5.3 | 99% | - | Fix |
| CVE-2018-11409 | Medium | 5.3 | 98% | - | - |
| CVE-2021-41277 | Critical | 10.0 | 97% | KEV | - |
| CVE-2016-2183 | High | 7.5 | 96% | - | Fix |
Common questions
How do I fix CVE-2026-53923?
Published advisories record a fix for 12 affected products. The "How to fix" section on this page lists the fixed version and source advisory for each one, so apply the entry matching what you actually run.
Is CVE-2026-53923 being actively exploited?
Not that we know of. CVE-2026-53923 is not in the CISA Known Exploited Vulnerabilities catalog. Its EPSS score of 0.48% is the estimated probability that it will be exploited in the next 30 days. That is higher than 40% of all scored CVEs.
How severe is CVE-2026-53923?
CVE-2026-53923 has a CVSS v3 base score of 7.5, rated high. CVSS rates the technical impact if the vulnerability is exploited, not how likely that is, so weigh it alongside the exploit-prediction score when you decide what to patch first.
What does CVE-2026-53923 affect?
Published advisories record a fix for registry.redhat.io/rhaiis/vllm (Red Hat / RHEL), registry.redhat.io/rhaiis/vllm (Rocky), registry.redhat.io/rhelai3/bootc (Red Hat / RHEL), registry.redhat.io/rhelai3/bootc (Rocky), and 8 more. Only products with a sourced advisory are listed, so treat this as what we can cite rather than a complete inventory.
Embed a live status badge for CVE-2026-53923
Markdown
[](https://tridentstack.com/cve/CVE-2026-53923)HTML
<a href="https://tridentstack.com/cve/CVE-2026-53923"><img src="https://tridentstack.com/cve/badge/CVE-2026-53923.svg" alt="CVE-2026-53923"></a>Check your Linux endpoints for this class of vulnerability
TridentStack Control continuously scans Linux endpoints for known vulnerabilities and deploys the fixes from the same console. 200 endpoints free forever, no credit card.
This product uses NVD data but is not endorsed or certified by the NVD. EPSS scores courtesy of FIRST.org (https://www.first.org/epss). Source: CISA KEV Catalog. Data as of 2026-06-24.