Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-19 01:04:55 +02:00
Code Issues Packages Projects Releases Wiki Activity

ci : add self-hosted webgpu to hf-jobs (#28712)

Browse Source 
* add self-hosted vulkan and webgpu to hf-jobs

* try t4-medium

* cont : adjust cpu backend threads

* try t4-small again

* restore cm jobs

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Sigbjørn Skjæret
2026-09-16 08:23:58 +02:00
committed by GitHub
parent e13469a323
commit 583926e3ac
2 changed files with 94 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-ops.cpp
+1 -2
View File
@@ -12000,8 +12000,7 @@ int main(int argc, char ** argv) {
ggml_backend_reg_t reg = ggml_backend_dev_backend_reg(dev);
auto ggml_backend_set_n_threads_fn = (ggml_backend_set_n_threads_t) ggml_backend_reg_get_proc_address(reg, "ggml_backend_set_n_threads");
if (ggml_backend_set_n_threads_fn) {
// TODO: better value for n_threads
ggml_backend_set_n_threads_fn(backend.get(), N_THREADS);
ggml_backend_set_n_threads_fn(backend.get(), std::max<int>(1, N_THREADS/2));
}
size_t free, total; // NOLINT