CVE-2026-53923
HighCVSS 7.5Exploitation Probability (EPSS)
Low risk24th percentile - higher than 24% of all known CVEs
Summary
vLLM, an inference and serving engine for large language models, has a vulnerability due to integer truncation of tensor dimensions, leading to partial tensor processing. As a result, the unfilled portion of the output tensor may contain data from GPU memory, leading to information disclosure.
Risk Assessment
In multi-tenant inference deployments, residual GPU memory may contain data from other users' inference requests, posing a serious risk of information disclosure.
Recommendation
It is recommended to update vLLM to version 0.23.1rc0 to eliminate this vulnerability and minimize the risk of data exposure.
Original NVD description (English source)
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.