git/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp synced 2026-04-30 03:01:52 +02:00
Code Issues Packages Projects Releases Wiki Activity

load directly from downloaded state

Browse Source
This commit is contained in:
Ruben Ortlam 2026-04-21 13:22:50 +02:00
parent b1623a614c
commit cf0ebc4e64
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tools/server/server-models.cpp
View File

@ -762,7 +762,6 @@ void server_models::load(const std::string & name) {
}
mem = meta.dmm_req;
}
update_status(name, SERVER_MODEL_STATUS_UNLOADED, 0);
try {
_load(name, mem);
} catch (const std::exception & e) {
@ -798,7 +797,7 @@ void server_models::_load(const std::string & name, const device_memory_map & dm
std::lock_guard<std::mutex> lk(mutex);
auto meta = mapping[name].meta;
if (meta.status != SERVER_MODEL_STATUS_UNLOADED) {
if (meta.status != SERVER_MODEL_STATUS_UNLOADED && meta.status != SERVER_MODEL_STATUS_DOWNLOADING) {
SRV_INF("model %s is not ready\n", name.c_str());
return;
}