ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

ggml : add metal backend registry / device (#9713)

Browse source 
* ggml : add metal backend registry / device

ggml-ci

* metal : fix names [no ci]

* metal : global registry and device instances

ggml-ci

* cont : alternative initialization of global objects

ggml-ci

* llama : adapt to backend changes

ggml-ci

* fixes

* metal : fix indent

* metal : fix build when MTLGPUFamilyApple3 is not available

ggml-ci

* fix merge

* metal : avoid unnecessary singleton accesses

ggml-ci

* metal : minor fix [no ci]

* metal : g_state -> g_ggml_ctx_dev_main [no ci]

* metal : avoid reference of device context in the backend context

ggml-ci

* metal : minor [no ci]

* metal : fix maxTransferRate check

* metal : remove transfer rate stuff

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov 2024-10-07 18:27:51 +03:00 • committed by GitHub
parent 96b6912103
commit d5ac8cf2f2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 535 additions and 284 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/include/ggml-backend.h
View file

@ -127,6 +127,8 @@ extern "C" {
bool async;
// pinned host buffer
bool host_buffer;
// creating buffers from host ptr
bool buffer_from_host_ptr;
// event synchronization
bool events;
};

6
ggml/include/ggml-metal.h
View file

@ -43,7 +43,9 @@ GGML_API ggml_backend_t ggml_backend_metal_init(void);
GGML_API bool ggml_backend_is_metal(ggml_backend_t backend);
GGML_API ggml_backend_buffer_t ggml_backend_metal_buffer_from_ptr(void * data, size_t size, size_t max_size);
GGML_DEPRECATED(
GGML_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/ggerganov/llama.cpp/pull/9713");
GGML_API void ggml_backend_metal_set_abort_callback(ggml_backend_t backend, ggml_abort_callback abort_callback, void * user_data);
@ -57,6 +59,8 @@ GGML_API bool ggml_backend_metal_supports_family(ggml_backend_t backend, int fam
// capture all command buffers committed the next time `ggml_backend_graph_compute` is called
GGML_API void ggml_backend_metal_capture_next_compute(ggml_backend_t backend);
GGML_API ggml_backend_reg_t ggml_backend_metal_reg(void);
#ifdef __cplusplus
}
#endif