VulnerabilityAnalyzed

CVE-2026-53923

In multi-tenant inference deployments, this residual GPU memory may contain tensor data from other users' inference requests, constituting information disclosure.

MEDIUM 5.3EPSS 0.48%

Does this matter?

Lower severity and a low EPSS score (0.48%). Track it; it rarely justifies an emergency change on its own.

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.

CVSS 4.0: 5.3 MEDIUMCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
EPSS: 0.48% probability · 40th percentile
CISA KEV: Not listed
Weakness: CWE-200, CWE-681
Affected: vllm/vllm
Source: security-advisories@github.com

References

https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225ePatch
https://github.com/vllm-project/vllm/pull/44971Issue Tracking
https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4Third Party Advisory

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.