# CVE-2026-53923

## Summary

- **CVE ID:** CVE-2026-53923
- **Severity:** MEDIUM
- **CVSS Score:** 5.3 (CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N)
- **CWE:** CWE-681, CWE-200
- **Published:** Jun 22, 2026
- **Last Modified:** Jun 23, 2026

## 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.

## Affected Products

- vllm-project — vllm (>= 0.5.5, < 0.23.1rc0)

## References

- [CNA](https://github.com/vllm-project/vllm/security/advisories/GHSA-5jv2-g5wq-cmr4)
- [CNA](https://github.com/vllm-project/vllm/pull/44971)
- [CNA](https://github.com/vllm-project/vllm/commit/f219788f91952827132fa4fdf916427cd20d225e)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.48%
- **EPSS Percentile:** 40.2

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-10._