upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

move it to ggml_backend_reg_i

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-07-03 16:35:19 +02:00
parent 4d990e1113
commit 7f88a1b9f9
3 changed files with 29 additions and 39 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
ggml/src/ggml-backend-impl.h
View File

@@ -221,6 +221,9 @@ extern "C" {
// (optional) get a pointer to a function in the backend
// backends can add custom functions that are not part of the standard ggml-backend interface
void * (*get_proc_address)(ggml_backend_reg_t reg, const char * name);
// (optional) free backend reg (before unloading the dynamic library)
void (*free)(ggml_backend_reg_t reg);
};
struct ggml_backend_reg {
@@ -236,8 +239,6 @@ extern "C" {
// Optional: obtain a score for the backend based on the system configuration
// Higher scores are preferred, 0 means the backend is not supported in the current system
typedef int (*ggml_backend_score_t)(void);
// Optional: release all resources held by the backend (before unloading the dynamic library)
typedef void (*ggml_backend_reg_free_t)(ggml_backend_reg_t reg);
#ifdef GGML_BACKEND_DL
# ifdef __cplusplus
@@ -255,13 +256,6 @@ extern "C" {
int ggml_backend_score(void) { \
return score_fn(); \
}
# define GGML_BACKEND_DL_FREE_IMPL(free_fn) \
extern "C" { \
GGML_BACKEND_API void ggml_backend_reg_free(ggml_backend_reg_t reg); \
} \
void ggml_backend_reg_free(ggml_backend_reg_t reg) { \
free_fn(reg); \
}
# else
# define GGML_BACKEND_DL_IMPL(reg_fn) \
GGML_BACKEND_API ggml_backend_reg_t ggml_backend_init(void); \
@@ -273,16 +267,10 @@ extern "C" {
int ggml_backend_score(void) { \
return score_fn(); \
}
# define GGML_BACKEND_DL_FREE_IMPL(free_fn) \
GGML_BACKEND_API void ggml_backend_reg_free(ggml_backend_reg_t reg); \
void ggml_backend_reg_free(ggml_backend_reg_t reg) { \
free_fn(reg); \
}
# endif
#else
# define GGML_BACKEND_DL_IMPL(reg_fn)
# define GGML_BACKEND_DL_SCORE_IMPL(score_fn)
# define GGML_BACKEND_DL_FREE_IMPL(free_fn)
#endif
#ifdef __cplusplus

7
ggml/src/ggml-backend-reg.cpp
View File

@@ -278,11 +278,8 @@ struct ggml_backend_registry {
devices.end());
// if backend supports free(), use it
if (it->handle) {
auto * free_fn = (ggml_backend_reg_free_t) dl_get_sym(it->handle.get(), "ggml_backend_reg_free");
if (free_fn) {
free_fn(reg);
}
if (reg->iface.free) {
reg->iface.free(reg);
}
// remove backend

43
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -5722,17 +5722,40 @@ static void * ggml_backend_cuda_reg_get_proc_address(ggml_backend_reg_t reg, con
return nullptr;
}
static bool ggml_backend_cuda_reg_initialized = false;
static void ggml_backend_cuda_reg_free(ggml_backend_reg_t reg) {
ggml_backend_cuda_reg_context * ctx = (ggml_backend_cuda_reg_context *) reg->context;
for (ggml_backend_dev_t dev : ctx->devices) {
int device = ((ggml_backend_cuda_device_context *) dev->context)->device;
delete (ggml_backend_cuda_device_context *) dev->context;
delete dev;
cudaError_t err = cudaSetDevice(device);
if (err == cudaSuccess) {
cudaDeviceReset();
}
}
delete ctx;
reg->context = nullptr;
ggml_backend_cuda_reg_initialized = false;
}
static const ggml_backend_reg_i ggml_backend_cuda_reg_interface = {
/* .get_name = */ ggml_backend_cuda_reg_get_name,
/* .get_device_count = */ ggml_backend_cuda_reg_get_device_count,
/* .get_device = */ ggml_backend_cuda_reg_get_device,
/* .get_proc_address = */ ggml_backend_cuda_reg_get_proc_address,
/* .free = */ ggml_backend_cuda_reg_free,
};
// backend registry
ggml_backend_reg_t ggml_backend_cuda_reg() {
static ggml_backend_reg reg;
static bool initialized = false;
bool & initialized = ggml_backend_cuda_reg_initialized;
{
static std::mutex mutex;
@@ -5779,23 +5802,6 @@ ggml_backend_reg_t ggml_backend_cuda_reg() {
return ®
}
static void ggml_backend_cuda_reg_free(ggml_backend_reg_t reg) {
ggml_backend_cuda_reg_context * ctx = (ggml_backend_cuda_reg_context *) reg->context;
for (ggml_backend_dev_t dev : ctx->devices) {
int device = ((ggml_backend_cuda_device_context *) dev->context)->device;
delete (ggml_backend_cuda_device_context *) dev->context;
delete dev;
cudaError_t err = cudaSetDevice(device);
if (err == cudaSuccess) {
cudaDeviceReset();
}
}
delete ctx;
}
ggml_backend_t ggml_backend_cuda_init(int device) {
if (device < 0 || device >= ggml_backend_cuda_get_device_count()) {
GGML_LOG_ERROR("%s: invalid device %d\n", __func__, device);
@@ -5819,4 +5825,3 @@ ggml_backend_t ggml_backend_cuda_init(int device) {
}
GGML_BACKEND_DL_IMPL(ggml_backend_cuda_reg)
GGML_BACKEND_DL_FREE_IMPL(ggml_backend_cuda_reg_free)