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

also allow terminate loading model

This commit is contained in:
Xuan Son Nguyen 2025-11-20 16:20:14 +01:00
parent 6610724f8e
commit d0ea9e0830
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tools/server/server-models.cpp
View File

@ -303,7 +303,7 @@ void server_models::unload(const std::string & name) {
std::lock_guard<std::mutex> lk(mutex);
auto it = mapping.find(name);
if (it != mapping.end()) {
if (it->second.meta.status == SERVER_MODEL_STATUS_LOADED) {
if (it->second.meta.status == SERVER_MODEL_STATUS_LOADED || it->second.meta.status == SERVER_MODEL_STATUS_LOADING) {
SRV_INF("unloading model instance name=%s\n", name.c_str());
subprocess_destroy(it->second.subproc.get());
// status change will be handled by the managing thread
@ -318,7 +318,7 @@ void server_models::unload_all() {
{
std::lock_guard<std::mutex> lk(mutex);
for (auto & [name, inst] : mapping) {
if (inst.meta.status == SERVER_MODEL_STATUS_LOADED) {
if (inst.meta.status == SERVER_MODEL_STATUS_LOADED || inst.meta.status == SERVER_MODEL_STATUS_LOADING) {
SRV_INF("unloading model instance name=%s\n", name.c_str());
subprocess_destroy(inst.subproc.get());
// status change will be handled by the managing thread