| ID |
CVE-2026-53923
|
| Sažetak |
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. |
| Reference |
|
| CVSS |
| Base: | 7.5 |
| Impact: | 3.6 |
| Exploitability: | 3.9 |
|
| Pristup |
| Vektor | Složenost | Autentikacija |
| NETWORK |
LOW |
NONE |
|
| Impact |
| Povjerljivost | Cjelovitost | Dostupnost |
| HIGH |
NONE |
NONE |
|
| CVSS vektor |
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N |
| Zadnje važnije ažuriranje |
24-06-2026 - 16:51 |
| Objavljeno |
22-06-2026 - 23:16 |
