AMD ROCm: handle UMA memory VRAM expansions

This resolves #2797 by allowing ROCm AMD GPU users with a UMA to
dynamically expand the VRAM allocated to the GPU.

Without this, AMD ROCm users with shared CPU/GPU memory usually are
stuck with the BIOS-set (or fixed) framebuffer VRAM, making it
impossible to load more than 1-2 layers.

Note that the model is duplicated in RAM because it's loaded once for
the CPU and then copied into a second set of allocations that are
managed by the HIP UMA system. We can fix this later.

ggml-cuda.cu

@@ -58,8 +58,8 @@
 #define cudaGetDeviceProperties hipGetDeviceProperties
 #define cudaGetErrorString hipGetErrorString
 #define cudaGetLastError hipGetLastError
-#define cudaMalloc hipMalloc
-#define cudaMallocHost(ptr, size) hipHostMalloc(ptr, size, hipHostMallocDefault)
+#define cudaMalloc(ptr, size) hipMallocManaged(ptr, size, hipMemAttachGlobal)
+#define cudaMallocHost(ptr, size) hipMallocHost(ptr, size)
 #define cudaMemcpy hipMemcpy
 #define cudaMemcpy2DAsync hipMemcpy2DAsync
 #define cudaMemcpyAsync hipMemcpyAsync