extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-10 04:29:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

sync : ggml (VMM, sync-ggml-am, dotprod ARM fixes, CUDA fixes) (#1691)

Browse Source 
* scripts : add sync-ggml-am.sh

* sync : ggml (VMM, ARM dot prod fix, etc.)

* build : fix CUDA build

* ggml : fix some mul mat cases + add tests for src1 F16

dbd02958fa
This commit is contained in:
Georgi Gerganov
2023-12-29 11:30:47 +02:00
committed by GitHub
parent a5cc3dc8a2
commit e77b27c331
9 changed files with 720 additions and 766 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
ggml-backend.c
View File

@ -297,7 +297,7 @@ static void ggml_backend_registry_init(void) {
void ggml_backend_register(const char * name, ggml_backend_init_fn init_fn, ggml_backend_buffer_type_t default_buffer_type, void * user_data) {
GGML_ASSERT(ggml_backend_registry_count < GGML_MAX_BACKENDS_REG);
int id = ggml_backend_registry_count;
size_t id = ggml_backend_registry_count;
ggml_backend_registry[id] = (struct ggml_backend_reg) {
/* .name = */ {0},
@ -330,6 +330,8 @@ size_t ggml_backend_reg_find_by_name(const char * name) {
return i;
}
}
// not found
return SIZE_MAX;
}
@ -340,15 +342,15 @@ ggml_backend_t ggml_backend_reg_init_backend_from_str(const char * backend_str)
const char * params = strchr(backend_str, ':');
char backend_name[128];
if (params == NULL) {
strcpy(backend_name, backend_str);
snprintf(backend_name, sizeof(backend_name), "%s", backend_str);
params = "";
} else {
strncpy(backend_name, backend_str, params - backend_str);
backend_name[params - backend_str] = '\0';
snprintf(backend_name, sizeof(backend_name), "%.*s", (int)(params - backend_str), backend_str);
params++;
}
size_t backend_i = ggml_backend_reg_find_by_name(backend_name);
if (backend_i == SIZE_MAX) {
fprintf(stderr, "%s: backend %s not found\n", __func__, backend_name);
return NULL;
@ -396,18 +398,12 @@ static void ggml_backend_cpu_buffer_free_buffer(ggml_backend_buffer_t buffer) {
}
static void ggml_backend_cpu_buffer_set_tensor(ggml_backend_buffer_t buffer, struct ggml_tensor * tensor, const void * data, size_t offset, size_t size) {
GGML_ASSERT(offset + size <= ggml_nbytes(tensor) && "tensor write out of bounds");
GGML_ASSERT(tensor->data != NULL && "tensor not allocated");
memcpy((char *)tensor->data + offset, data, size);
GGML_UNUSED(buffer);
}
static void ggml_backend_cpu_buffer_get_tensor(ggml_backend_buffer_t buffer, const struct ggml_tensor * tensor, void * data, size_t offset, size_t size) {
GGML_ASSERT(offset + size <= ggml_nbytes(tensor) && "tensor read out of bounds");
GGML_ASSERT(tensor->data != NULL && "tensor not allocated");
memcpy(data, (const char *)tensor->data + offset, size);
GGML_UNUSED(buffer);
@ -618,10 +614,14 @@ static void ggml_backend_cpu_graph_compute(ggml_backend_t backend, struct ggml_c
}
static bool ggml_backend_cpu_supports_op(ggml_backend_t backend, const struct ggml_tensor * op) {
return true;
switch (op->op) {
case GGML_OP_MUL_MAT:
return op->src[1]->type == GGML_TYPE_F32 || op->src[1]->type == ggml_internal_get_type_traits(op->src[0]->type).vec_dot_type;
default:
return true;
}
GGML_UNUSED(backend);
GGML_UNUSED(op);
}
static struct ggml_backend_i cpu_backend_i = {