thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

common : move up common_init() and fix Windows UTF-8 logs (#21176)

Browse source 
The build info is now only for debug, so we avoid the duplicate
with `--version`.

The UTF-8 setup at the beginning is needed to avoid logging
garbage on Windows.

Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët 2026-03-31 12:53:41 +02:00 • committed by GitHub
parent 62278cedde
commit 41361c8599
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
34 changed files with 73 additions and 55 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/training/finetune.cpp
View file

@ -20,6 +20,8 @@ int main(int argc, char ** argv) {
common_params params;
params.escape = false;
common_init();
if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_FINETUNE)) {
return 1;
}
@ -38,7 +40,6 @@ int main(int argc, char ** argv) {
params.cache_type_v = GGML_TYPE_F32;
}
common_init();
llama_backend_init();
llama_numa_init(params.numa);
// load the model and apply lora adapter, if any