Skip to content

LLM inference in C/C++

C++ ggml

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

Aritro Bandyopadhyay8a832e4bf328
diff --git a/tools/server/server.cpp b/tools/server/server.cpp
index 01cc6633a3..230b578e07 100644
--- a/tools/server/server.cpp
+++ b/tools/server/server.cpp
@@ -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);