metal : make the backend async (ggml-org#15906)

* metal : make the backend async

ggml-ci

* cont : add comments, extend op offload, clean up

ggml-ci

* metal : fix batch size for MUL_MAT_ID

* metal : remove deprecated ggml_backend_metal_buffer_from_ptr

* metal : create only metal buffers, no wrapping of host memory

ggml-ci

* metal : restore .alloc_buffer for buffer_from_ptr_type

ggml-ci

* metal : remove broken implementation of GGML_OP_SET

ggml-ci

* metal : clean-up loose ends, ready for tests

ggml-ci

* metal : support both private and shared buffers

ggml-ci

* metal : enable private buffers + add global device queue

* metal : disable host buffer to prevent races

ggml-ci

* metal : avoid extra copy during set_tensor

ggml-ci

* metal : use separate buffer types for shread and private Metal buffers

ggml-ci

* metal : simplify synchronization logic

ggml-ci

* metal : fix build

ggml-ci

* metal : do not implement cpy_tensor

ggml-ci

* metal : separate implementations for shared and private buffers

ggml-ci

Author: ggerganov

ggml/include/ggml-metal.h

@@ -43,14 +43,8 @@ GGML_BACKEND_API ggml_backend_t ggml_backend_metal_init(void);
 
 GGML_BACKEND_API bool ggml_backend_is_metal(ggml_backend_t backend);
 
-GGML_DEPRECATED(
-        GGML_BACKEND_API ggml_backend_buffer_t ggml_backend_metal_buffer_from_ptr(void * data, size_t size, size_t max_size),
-        "obsoleted by the new device interface - https://github.com/ggml-org/llama.cpp/pull/9713");
-
 GGML_BACKEND_API void ggml_backend_metal_set_abort_callback(ggml_backend_t backend, ggml_abort_callback abort_callback, void * user_data);
 
-GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_metal_buffer_type(void);
-
 // helper to check if the device supports a specific family
 // ideally, the user code should be doing these checks
 // ref: https://developer.apple.com/metal/Metal-Feature-Set-Tables.pdf