Yüksek CVSS 7.5
CVE-2026-53923: Vllm: hassas bilgi ifşası
Açıklama (NVD)
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.
Özet bilgiler
- Ürün
- Vllm Vllm
- CVSS v3.1
- 7.5
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - CVSS v4.0
- 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - EPSS
- %0,48 (yüzdelik 42)
- CWE
- CWE-200
- Yama
- Mevcut
Etkilenen sürümler
| Ürün | Başlangıç | Bitiş | Düzeltildi |
|---|---|---|---|
| vllm-vllm | 0.5.5 | — | 0.23.1 |