Jaime Fournier
Jaime Fournier
This is also seen on Linux and FreeBSD.
yes we can.
This is fantastic. Just get this on FreeBSD with 10GB vram. ggml_vulkan: Memory allocation of size 430940160 failed. ggml_vulkan: vk::Device::allocateMemory: ErrorOutOfDeviceMemory llama_model_load: error loading model: vk::Device::allocateMemory: ErrorOutOfDeviceMemory llama_load_model_from_file: exception loading...
:+1: This bit me on a 5 hour build.