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

presets: refactor, allow cascade presets from different sources, add global section (#18169)

Browse source 
* presets: refactor, allow cascade presets from different sources

* update docs

* fix neg arg handling

* fix empty mmproj

* also filter out server-controlled args before to_ini()

* skip loading custom_models if not specified

* fix unset_reserved_args

* fix crash on windows
This commit is contained in:
Xuan-Son Nguyen 2025-12-19 12:08:20 +01:00 • committed by GitHub
parent acb73d8340
commit 98c1c7a7bf
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 353 additions and 260 deletions
Download patch file Download diff file Expand all files Collapse all files

5
common/arg.cpp
View file

@ -772,6 +772,11 @@ bool common_params_to_map(int argc, char ** argv, llama_example ex, std::map<com
}
auto opt = *arg_to_options[arg];
std::string val;
if (opt.value_hint == nullptr && opt.value_hint_2 == nullptr) {
// bool arg (need to reverse the meaning for negative args)
bool is_neg = std::find(opt.args_neg.begin(), opt.args_neg.end(), arg) != opt.args_neg.end();
val = is_neg ? "0" : "1";
}
if (opt.value_hint != nullptr) {
// arg with single value
check_arg(i);