mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
metal : make the backend async (#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
This commit is contained in:
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user