CVE-2026-86288

A vulnerability has been found in ModelCloud GPTQModel up to 7.2.0. This vulnerability affects unknown code of the file gptqmodel/nnmodules/qlinear/tritonv2.py of the component Triton dequantization kernel. Such manipulation of the argument gidx leads to out-of-bounds read. The attack can be...

CVE-2026-86288

ModelCloud GPTQModel versions up to 7.2.0 contain an out-of-bounds read vulnerability in the Triton dequantization kernel (gptqmodel/nn_modules/qlinear/tritonv2.py). The root cause is improper handling of the g_idx argument, which can be manipulated by an unauthenticated remote attacker (with use...

CVE-2026-86288 ModelCloud GPTQModel Triton dequantization kernel tritonv2.py out-of-bounds

A vulnerability has been found in ModelCloud GPTQModel up to 7.2.0. This vulnerability affects unknown code of the file gptqmodel/nnmodules/qlinear/tritonv2.py of the component Triton dequantization kernel. Such manipulation of the argument gidx leads to out-of-bounds read. The attack can be...

CVE-2026-53923 vLLM GGUF Kernels: int64_t to int truncation of tensor dimensions causes GPU buffer overflow

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/ggufkernel.cu causes partial tensor processing. The output tensor is allocated at full size via...

SUSE CVE-2017-14409

A buffer overflow was discovered in IIIdequantizesample in layer3.c in mpglibDBL, as used in MP3Gain version 1.5.2. The vulnerability causes an out-of-bounds write, which leads to remote denial of service or possibly code execution...