vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 17:14:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'master' into concedo_experimental

Browse source
This commit is contained in:
Concedo 2023-06-12 21:53:13 +08:00
commit 215edf420b
6 changed files with 57 additions and 115 deletions
Download patch file Download diff file Expand all files Collapse all files

35
ggml-opencl.cpp
View file

@ -1682,7 +1682,7 @@ size_t ggml_cl_mul_mat_get_wsize(const struct ggml_tensor * src0, const struct g
return 0;
}
void ggml_cl_transform_tensor(ggml_tensor * tensor) {
void ggml_cl_transform_tensor(void * data, ggml_tensor * tensor) {
const int64_t ne0 = tensor->ne[0];
const int64_t ne1 = tensor->ne[1];
const int64_t ne2 = tensor->ne[2];
@ -1694,6 +1694,7 @@ void ggml_cl_transform_tensor(ggml_tensor * tensor) {
size_t q_size;
cl_mem dst = ggml_cl_pool_malloc(q_sz, &q_size);
tensor->data = data;
// copy tensor to device
for (int64_t i3 = 0; i3 < ne3; i3++) {
for (int64_t i2 = 0; i2 < ne2; i2++) {
@ -1705,35 +1706,5 @@ void ggml_cl_transform_tensor(ggml_tensor * tensor) {
CL_CHECK(clFinish(queue));
tensor->data = dst;
tensor->backend = GGML_BACKEND_GPU;
}
void ggml_cl_load_data(const char * fname, struct ggml_tensor * tensor, const size_t offset) {
cl_int err;
FILE * fp = fopen(fname, "rb");
const size_t size = ggml_nbytes(tensor);
cl_mem dst;
CL_CHECK((dst = clCreateBuffer(context, CL_MEM_READ_ONLY, size, nullptr, &err), err));
void * buf_host = malloc(size);
#ifdef _WIN32
int ret = _fseeki64(fp, (__int64) offset, SEEK_SET);
#else
int ret = fseek(fp, (long) offset, SEEK_SET);
#endif
GGML_ASSERT(ret == 0); // same
size_t ret2 = fread(buf_host, size, 1, fp);
if (ret2 != 1) {
fprintf(stderr, "unexpectedly reached end of file");
exit(1);
}
clEnqueueWriteBuffer(queue, dst, CL_TRUE, 0, size, buf_host, 0, nullptr, nullptr);
tensor->data = dst;
free(buf_host);
fclose(fp);
GGML_ASSERT(tensor->backend == GGML_BACKEND_GPU);
}