Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-08-25 22:21:03 +02:00
Code Issues Packages Projects Releases Wiki Activity

server : fix --docker-repo being treated as router mode (#27416)

Browse Source
This commit is contained in:
Aritro Bandyopadhyay
2026-08-20 06:37:14 -06:00
committed by GitHub
parent 2b5621094e
commit 8a832e4bf3
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server.cpp
+2 -1
View File
@@ -133,7 +133,8 @@ int llama_server(common_params & params, int argc, char ** argv) {
// router server never loads a model and must not touch the GPU
const bool is_router_server = params.model.path.empty()
&& params.model.hf_repo.empty();
&& params.model.hf_repo.empty()
&& params.model.docker_repo.empty();
// skip device enumeration so the CUDA primary context stays uncreated
common_params_print_info(params, !is_router_server);