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

metal : remove old API (#4919)

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-01-13 20:45:45 +02:00 • committed by GitHub
parent 0ea069b87b
commit 4be5ef556d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 27 additions and 427 deletions
Download patch file Download diff file Expand all files Collapse all files

55
ggml-metal.h
View file

@ -36,64 +36,13 @@ struct ggml_cgraph;
extern "C" {
#endif
//
// internal API
// temporary exposed to user-code
//
struct ggml_metal_context;
void ggml_metal_log_set_callback(ggml_log_callback log_callback, void * user_data);
// number of command buffers to use
struct ggml_metal_context * ggml_metal_init(int n_cb);
void ggml_metal_free(struct ggml_metal_context * ctx);
void * ggml_metal_host_malloc(size_t n);
void ggml_metal_host_free (void * data);
// set the number of command buffers to use
void ggml_metal_set_n_cb(struct ggml_metal_context * ctx, int n_cb);
// creates a mapping between a host memory buffer and a device memory buffer
// - make sure to map all buffers used in the graph before calling ggml_metal_graph_compute
// - the mapping is used during computation to determine the arguments of the compute kernels
// - you don't need to keep the host memory buffer allocated as it is never accessed by Metal
// - max_size specifies the maximum size of a tensor and is used to create shared views such
// that it is guaranteed that the tensor will fit in at least one of the views
//
bool ggml_metal_add_buffer(
struct ggml_metal_context * ctx,
const char * name,
void * data,
size_t size,
size_t max_size);
// set data from host memory into the device
void ggml_metal_set_tensor(struct ggml_metal_context * ctx, struct ggml_tensor * t);
// get data from the device into host memory
void ggml_metal_get_tensor(struct ggml_metal_context * ctx, struct ggml_tensor * t);
// try to find operations that can be run concurrently in the graph
// you should run it again if the topology of your graph changes
void ggml_metal_graph_find_concurrency(struct ggml_metal_context * ctx, struct ggml_cgraph * gf, bool check_mem);
// if the graph has been optimized for concurrently dispatch, return length of the concur_list if optimized
int ggml_metal_if_optimized(struct ggml_metal_context * ctx);
// output the concur_list for ggml_alloc
int * ggml_metal_get_concur_list(struct ggml_metal_context * ctx);
// same as ggml_graph_compute but uses Metal
// creates gf->n_threads command buffers in parallel
bool ggml_metal_graph_compute(struct ggml_metal_context * ctx, struct ggml_cgraph * gf);
//
// backend API
// user-code should use only these functions
//
GGML_API void ggml_backend_metal_log_set_callback(ggml_log_callback log_callback, void * user_data);
GGML_API ggml_backend_t ggml_backend_metal_init(void);
GGML_API bool ggml_backend_is_metal(ggml_backend_t backend);