Information disclosure in Vllm

CVE-2026-53923

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.

Vulnerability class: Information Disclosure

Published · last modified .

CVSS v3 metric

CVSS v3 base score 7.5 (High). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N.

EPSS exploit prediction

EPSS: 0.005 (39.3th percentile), scored .

Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 39th percentile — 39.3% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.

EPSS trend (30 days)EPSS over the last 30 days for CVE-2026-53923: held from 0.005 to 0.005.

EPSS over last 30 days · oldest: 0.005 · newest: 0.005 · change: 0.000

Affected products

Weakness classification (CWE)

References

Frequently asked questions

What is CVE-2026-53923?
CVE-2026-53923 is a high-severity vulnerability in Vllm, classified under Information Disclosure. CVSS score: 7.5/10. Published 2026-06-22.
How severe is CVE-2026-53923?
High severity. CVSS v3 base score is 7.5 out of 10.