2 matches found
PT-2026-60015
Summary 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...
7.5CVSS6.2AI score0.00484EPSS
SaveExploits0References8
SUSE CVE-2019-11751
Logging-related command line parameters are not properly sanitized when Firefox is launched by another program, such as when a user clicks on malicious links in a chat application. This can be used to write a log file to an arbitrary location such as the Windows 'Startup' folder. Note: this issue...
8.8CVSS8.4AI score0.01062EPSS
SaveExploits0References11
20