Vulkan: Set device max size for host memory to avoid OOM warning and fallback to CPU buffer (llama/14249)

ggml/src/ggml-vulkan/ggml-vulkan.cpp

@@ -9495,6 +9495,12 @@ static size_t ggml_backend_vk_host_buffer_type_get_alignment(ggml_backend_buffer
     UNUSED(buft);
 }
 
+static size_t ggml_backend_vk_host_buffer_type_get_max_size(ggml_backend_buffer_type_t buft) {
+    return vk_instance.devices[0]->suballocation_block_size;
+
+    UNUSED(buft);
+}
+
 // Should be changed to return device-specific host buffer type
 // but that probably requires changes in llama.cpp
 ggml_backend_buffer_type_t ggml_backend_vk_host_buffer_type() {
@@ -9503,7 +9509,7 @@ ggml_backend_buffer_type_t ggml_backend_vk_host_buffer_type() {
             /* .get_name         = */ ggml_backend_vk_host_buffer_type_name,
             /* .alloc_buffer     = */ ggml_backend_vk_host_buffer_type_alloc_buffer,
             /* .get_alignment    = */ ggml_backend_vk_host_buffer_type_get_alignment,
-            /* .get_max_size     = */ NULL, // defaults to SIZE_MAX
+            /* .get_max_size     = */ ggml_backend_vk_host_buffer_type_get_max_size,
             /* .get_alloc_size   = */ ggml_backend_cpu_buffer_type()->iface.get_alloc_size,
             /* .is_host          = */ ggml_backend_cpu_buffer_type()->iface.is_host,
         },