Open-Source Security Intelligence

Know every vulnerability
before it knows you.

DevGuard continuously monitors your dependencies and alerts you when CVEs like this one affect your stack — with real-time threat intelligence built for developers.

Search

CVE-2026-53923

MediumCVSS 5.3 / 10
Published Jun 22, 2026·Last modified Jul 8, 2026
Affected Components(0)

No affected components available

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.

Risk Scores
Base Score
5.3

The vulnerability can be exploited over the network without needing physical access. It is easy for an attacker to exploit this vulnerability. An attacker does not need any special privileges or access rights.

Threat Intelligence
1.3

Limited exploitation activity has been observed. Close monitoring and planned remediation are recommended.

EPSS
0.28%

The exploit probability is very low. The vulnerability is unlikely to be exploited in the next 30 days.

Exploit
Not available

We did not find any exploit available. Neither in GitHub repositories nor in the Exploit-Database.

Scan your project

Continuously monitor your dependencies and get alerted when vulnerabilities like this one affect your stack.

Checkout DevGuard