mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-11 04:56:56 +02:00
fix common_params_print_info
This commit is contained in:
@@ -1948,7 +1948,7 @@ static void server_proc_restart(char ** argv, const char * env_name, const std::
|
||||
return;
|
||||
}
|
||||
|
||||
setenv(env_name, env_value.c_str(), 1);
|
||||
common_set_env(env_name, env_value);
|
||||
|
||||
const std::string exe = server_proc_exe_path(argv);
|
||||
SRV_INF("restarting the process, exe = '%s'\n", exe.c_str());
|
||||
@@ -1974,8 +1974,8 @@ void server_sleep_rst::init(int argc, char ** argv) {
|
||||
|
||||
this->argv = argv;
|
||||
|
||||
const char * state = std::getenv(SLEEP_STATE_ENV);
|
||||
if (state == nullptr) {
|
||||
const std::string state = common_get_env(SLEEP_STATE_ENV);
|
||||
if (state.empty()) {
|
||||
return;
|
||||
}
|
||||
|
||||
@@ -1985,12 +1985,8 @@ void server_sleep_rst::init(int argc, char ** argv) {
|
||||
SRV_ERR("failed to read the state left by the previous process: %s\n", e.what());
|
||||
}
|
||||
|
||||
#if defined(_WIN32)
|
||||
_putenv_s(SLEEP_STATE_ENV, "");
|
||||
#else
|
||||
// clear it now, so that child processes do not inherit it
|
||||
unsetenv(SLEEP_STATE_ENV);
|
||||
#endif
|
||||
common_set_env(SLEEP_STATE_ENV, "");
|
||||
}
|
||||
|
||||
void server_sleep_rst::enable(common_params & params) {
|
||||
@@ -2014,6 +2010,10 @@ void server_sleep_rst::enable(common_params & params) {
|
||||
enabled = true;
|
||||
}
|
||||
|
||||
bool server_sleep_rst::is_boot_to_sleep() {
|
||||
return !common_get_env(SLEEP_STATE_ENV).empty();
|
||||
}
|
||||
|
||||
void server_sleep_rst::restart() const {
|
||||
if (!enabled) {
|
||||
return;
|
||||
|
||||
@@ -619,6 +619,10 @@ struct server_pipe {
|
||||
//
|
||||
|
||||
struct server_sleep_rst {
|
||||
// true if the process was restarted by a previous instance
|
||||
// in this case, the model is only loaded upon the first request
|
||||
static bool is_boot_to_sleep();
|
||||
|
||||
// remember argv and read the state left by the previous process
|
||||
// must be called once at startup, before spawning any thread or child process
|
||||
void init(int argc, char ** argv);
|
||||
@@ -626,10 +630,6 @@ struct server_sleep_rst {
|
||||
// enable the restart upon sleeping, warns and falls back to --sleep-mode free if not possible
|
||||
void enable(common_params & params);
|
||||
|
||||
// true if the process was restarted by a previous instance
|
||||
// in this case, the model is only loaded upon the first request
|
||||
bool is_boot_to_sleep() const { return !boot_state.is_null(); }
|
||||
|
||||
// state left by the previous process, only valid if is_boot_to_sleep()
|
||||
const json & get_boot_state() const { return boot_state; }
|
||||
|
||||
|
||||
@@ -132,8 +132,10 @@ int llama_server(common_params & params, int argc, char ** argv) {
|
||||
const bool is_router_server = params.model.path.empty()
|
||||
&& params.model.hf_repo.empty();
|
||||
|
||||
// skip device enumeration so the CUDA primary context stays uncreated
|
||||
common_params_print_info(params, !is_router_server);
|
||||
// may skip device enumeration so the CUDA primary context stays uncreated
|
||||
if (!server_sleep_rst::is_boot_to_sleep()) {
|
||||
common_params_print_info(params, !is_router_server);
|
||||
}
|
||||
|
||||
if (!is_router_server) {
|
||||
// validate batch size for embeddings
|
||||
|
||||
Reference in New Issue
Block a user