Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 09:38:55 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/close-issue.yml
#	.github/workflows/nix-ci-aarch64.yml
#	.github/workflows/nix-ci.yml
#	README.md
#	ci/run.sh
#	examples/server/README.md
#	ggml/src/ggml-cuda.cu
#	ggml/src/ggml-metal.m
#	scripts/sync-ggml.last
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo
2024-10-05 22:24:08 +08:00
parent 3e1cbedbae 8c475b97b8
commit da6cf261a8
28 changed files with 725 additions and 421 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/include/ggml-alloc.h
+1 -1
View File
@@ -24,7 +24,7 @@ GGML_API void ggml_tallocr_alloc(struct ggml_tallocr * talloc, st
// Graph allocator
/*
Example usage:
ggml_gallocr_t galloc = ggml_gallocr_new(ggml_bacckend_cpu_buffer_type());
ggml_gallocr_t galloc = ggml_gallocr_new(ggml_backend_cpu_buffer_type());
// optional: create a worst-case graph and reserve the buffers to avoid reallocations
ggml_gallocr_reserve(galloc, build_graph(max_batch));
ggml/include/ggml-backend.h
+3 -6
View File
@@ -164,7 +164,7 @@ extern "C" {
GGML_API size_t ggml_backend_reg_dev_count(ggml_backend_reg_t reg);
GGML_API ggml_backend_dev_t ggml_backend_reg_dev_get(ggml_backend_reg_t reg, size_t index);
GGML_API void * ggml_backend_reg_get_proc_address(ggml_backend_reg_t reg, const char * name);
GGML_API void ggml_backend_reg_set_log_callback(ggml_backend_reg_t reg, ggml_log_callback log_callback, void * user_data);
// Functions that may be obtained using ggml_backend_reg_get_proc_address
typedef ggml_backend_buffer_type_t (*ggml_backend_split_buffer_type_t)(const float *);
@@ -184,9 +184,6 @@ extern "C" {
GGML_API ggml_backend_dev_t ggml_backend_dev_by_name(const char * name);
GGML_API ggml_backend_dev_t ggml_backend_dev_by_type(enum ggml_backend_dev_type type);
// Set the log callback for all registered backends
GGML_API void ggml_backend_set_log_callback(ggml_log_callback log_callback, void * user_data);
// Direct backend (stream) initialization
// = ggml_backend_dev_init(ggml_backend_dev_by_name(name), params)
GGML_API ggml_backend_t ggml_backend_init_by_name(const char * name, const char * params);
@@ -250,7 +247,7 @@ extern "C" {
GGML_API void ggml_backend_sched_free(ggml_backend_sched_t sched);
// Initialize backend buffers from a measure graph
GGML_API bool ggml_backend_sched_reserve(ggml_backend_sched_t sched, struct ggml_cgraph * measure_graph);
GGML_API bool ggml_backend_sched_reserve(ggml_backend_sched_t sched, struct ggml_cgraph * measure_graph); // returns success
GGML_API int ggml_backend_sched_get_n_backends(ggml_backend_sched_t sched);
GGML_API ggml_backend_t ggml_backend_sched_get_backend(ggml_backend_sched_t sched, int i);
@@ -265,7 +262,7 @@ extern "C" {
GGML_API ggml_backend_t ggml_backend_sched_get_tensor_backend(ggml_backend_sched_t sched, struct ggml_tensor * node);
// Allocate and compute graph on the backend scheduler
GGML_API bool ggml_backend_sched_alloc_graph(ggml_backend_sched_t sched, struct ggml_cgraph * graph);
GGML_API bool ggml_backend_sched_alloc_graph(ggml_backend_sched_t sched, struct ggml_cgraph * graph); // returns success
GGML_API enum ggml_status ggml_backend_sched_graph_compute(ggml_backend_sched_t sched, struct ggml_cgraph * graph);
GGML_API enum ggml_status ggml_backend_sched_graph_compute_async(ggml_backend_sched_t sched, struct ggml_cgraph * graph);
GGML_API void ggml_backend_sched_synchronize(ggml_backend_sched_t sched);
ggml/include/ggml-cann.h
-11
View File
@@ -116,17 +116,6 @@ GGML_API void ggml_backend_cann_get_device_memory(int32_t device,
size_t* free,
size_t* total);
/**
* @brief Set the logging callback for GGML.
*
* This function sets the logging callback and user data for logging.
*
* @param log_callback The logging callback to set.
* @param user_data User data to pass to the logging callback.
*/
GGML_API void ggml_backend_cann_log_set_callback(ggml_log_callback log_callback,
void* user_data);
#ifdef __cplusplus
}
#endif
ggml/include/ggml-cuda.h
-2
View File
@@ -41,8 +41,6 @@ GGML_API void ggml_backend_cuda_get_device_memory(int device, size_t * free, siz
GGML_API bool ggml_backend_cuda_register_host_buffer(void * buffer, size_t size);
GGML_API void ggml_backend_cuda_unregister_host_buffer(void * buffer);
GGML_API void ggml_backend_cuda_log_set_callback(ggml_log_callback log_callback, void * user_data);
GGML_API ggml_backend_reg_t ggml_backend_cuda_reg(void);
#ifdef __cplusplus
ggml/include/ggml-metal.h
-2
View File
@@ -39,8 +39,6 @@ extern "C" {
// 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);
ggml/include/ggml.h
+11
View File
@@ -462,6 +462,7 @@ extern "C" {
GGML_OP_SUM_ROWS,
GGML_OP_MEAN,
GGML_OP_ARGMAX,
GGML_OP_COUNT_EQUAL,
GGML_OP_REPEAT,
GGML_OP_REPEAT_BACK,
GGML_OP_CONCAT,
@@ -1000,6 +1001,12 @@ extern "C" {
struct ggml_context * ctx,
struct ggml_tensor * a);
// count number of equal elements in a and b
GGML_API struct ggml_tensor * ggml_count_equal(
struct ggml_context * ctx,
struct ggml_tensor * a,
struct ggml_tensor * b);
// if a is the same shape as b, and a is not parameter, return a
// otherwise, return a new tensor: repeat(a) to fit in b
GGML_API struct ggml_tensor * ggml_repeat(
@@ -2173,6 +2180,10 @@ extern "C" {
typedef void (*ggml_opt_callback)(void * data, int accum_step, float * sched, bool * cancel);
typedef void (*ggml_log_callback)(enum ggml_log_level level, const char * text, void * user_data);
// Set callback for all future logging events.
// If this is not called, or NULL is supplied, everything is output on stderr.
GGML_API void ggml_log_set(ggml_log_callback log_callback, void * user_data);
// optimization parameters
//
// see ggml.c (ggml_opt_default_params) for default values