llama.cpp version b9686 fixes a segfault error that occurred with long prompts on the Eagle3 model. The release includes binaries for macOS, Linux, Android, Windows, and openEuler across multiple architectures and hardware acceleration options, including Vulkan, CUDA, OpenVINO, and SYCL.
llama.cpp Release b9686: Fixes Segfault on Long Prompts for Eagle3
from English