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, 42.3th percentile (scored ); unchanged over 30 days. About EPSS.
Affected products
- Vllm
- Vllm-Project Vllm — versions >= 0.5.5, < 0.23.1rc0