server: skip unused log lines on router mode (#24463)
This commit is contained in:
@@ -94,6 +94,7 @@ int llama_server(int argc, char ** argv) {
|
||||
const bool is_router_server = params.model.path.empty();
|
||||
common_params_print_info(params, !is_router_server);
|
||||
|
||||
if (!is_router_server) {
|
||||
// validate batch size for embeddings
|
||||
// embeddings require all tokens to be processed in a single ubatch
|
||||
// see https://github.com/ggml-org/llama.cpp/issues/12836
|
||||
@@ -109,6 +110,7 @@ int llama_server(int argc, char ** argv) {
|
||||
params.n_parallel = 4;
|
||||
params.kv_unified = true;
|
||||
}
|
||||
}
|
||||
|
||||
// for consistency between server router mode and single-model mode, we set the same model name as alias
|
||||
if (params.model_alias.empty() && !params.model.name.empty()) {
|
||||
|
||||
Reference in New Issue
Block a user