tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 12:35:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : reduce command encoding overhead (#9698)

Browse Source 
* metal : reduce command encoding overhead

ggml-ci

* metal : add comments
This commit is contained in:
Georgi Gerganov
2024-10-01 16:00:25 +03:00
committed by GitHub
parent a90484c6d9
commit cad341d889
5 changed files with 2000 additions and 1912 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/cvector-generator/pca.hpp
View File

@ -204,13 +204,6 @@ static ggml_status compute_piter(
ggml_backend_cpu_set_n_threads(model.backend, params.n_threads);
}
// TODO: enable GPU support when support for GGML_OP_SQRT is added
//#ifdef GGML_USE_METAL
// if (ggml_backend_is_metal(model.backend)) {
// ggml_backend_metal_set_n_cb(model.backend, params.n_threads);
// }
//#endif
ggml_status res = ggml_backend_graph_compute(model.backend, gf);
if (res == GGML_STATUS_SUCCESS) {
auto extract_i = [](std::string prefix, std::string str) -> int {