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

metal : reduce command encoding overhead (#9698)

Browse source 
* metal : reduce command encoding overhead

ggml-ci

* metal : add comments
This commit is contained in:
Georgi Gerganov 2024-10-01 16:00:25 +03:00 • committed by GitHub
parent a90484c6d9
commit cad341d889
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 2000 additions and 1912 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ggml/include/ggml-metal.h
View file

@ -25,9 +25,6 @@
#include <stddef.h>
#include <stdbool.h>
// max memory buffers that can be mapped to the device
#define GGML_METAL_MAX_BUFFERS 64
struct ggml_tensor;
struct ggml_cgraph;
@ -48,8 +45,6 @@ GGML_API bool ggml_backend_is_metal(ggml_backend_t backend);
GGML_API GGML_CALL ggml_backend_buffer_t ggml_backend_metal_buffer_from_ptr(void * data, size_t size, size_t max_size);
GGML_API void ggml_backend_metal_set_n_cb(ggml_backend_t backend, int n_cb);
GGML_API void ggml_backend_metal_set_abort_callback(ggml_backend_t backend, ggml_abort_callback abort_callback, void * user_data);
GGML_API GGML_CALL ggml_backend_buffer_type_t ggml_backend_metal_buffer_type(void);