happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix duplicated arg

This commit is contained in:
Xuan Son Nguyen 2025-11-30 14:53:47 +01:00
parent 802e77eaf4
commit 7b28b5e16a
1 changed files with 20 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
tools/server/server-models.cpp
View File

@ -324,6 +324,18 @@ void server_models::unload_lru() {
} }
} }
static void add_or_replace_arg(std::vector<std::string> & args, const std::string & key, const std::string & value) {
for (size_t i = 0; i < args.size(); i++) {
if (args[i] == key && i + 1 < args.size()) {
args[i + 1] = value;
return;
}
}
// not found, append
args.push_back(key);
args.push_back(value);
}
void server_models::load(const std::string & name, bool auto_load) { void server_models::load(const std::string & name, bool auto_load) {
if (!has_model(name)) { if (!has_model(name)) {
throw std::runtime_error("model name=" + name + " is not found"); throw std::runtime_error("model name=" + name + " is not found");
@ -356,33 +368,23 @@ void server_models::load(const std::string & name, bool auto_load) {
std::vector<std::string> child_args; std::vector<std::string> child_args;
if (auto_load && !meta.args.empty()) { if (auto_load && !meta.args.empty()) {
child_args = meta.args; // reuse previous args child_args = meta.args; // copy previous args
// update port arg
for (size_t i = 0; i < child_args.size(); i++) {
if (child_args[i] == "--port" && i + 1 < child_args.size()) {
child_args[i + 1] = std::to_string(inst.meta.port);
break;
}
}
} else { } else {
child_args = base_args; // copy child_args = base_args; // copy
if (inst.meta.in_cache) { if (inst.meta.in_cache) {
child_args.push_back("-hf"); add_or_replace_arg(child_args, "-hf", inst.meta.name);
child_args.push_back(inst.meta.name);
} else { } else {
child_args.push_back("-m"); add_or_replace_arg(child_args, "-m", inst.meta.path);
child_args.push_back(inst.meta.path);
if (!inst.meta.path_mmproj.empty()) { if (!inst.meta.path_mmproj.empty()) {
child_args.push_back("--mmproj"); add_or_replace_arg(child_args, "--mmproj", inst.meta.path_mmproj);
child_args.push_back(inst.meta.path_mmproj);
} }
} }
child_args.push_back("--alias");
child_args.push_back(inst.meta.name);
child_args.push_back("--port");
child_args.push_back(std::to_string(inst.meta.port));
} }
// set model args
add_or_replace_arg(child_args, "--port", std::to_string(inst.meta.port));
add_or_replace_arg(child_args, "--alias", inst.meta.name);
std::vector<std::string> child_env = base_env; // copy std::vector<std::string> child_env = base_env; // copy
child_env.push_back("LLAMA_SERVER_ROUTER_PORT=" + std::to_string(base_params.port)); child_env.push_back("LLAMA_SERVER_ROUTER_PORT=" + std::to_string(base_params.port));