server : update `/props` with "total_slots" value (#5373)

* include total "num_slots" in default_generation_settings_for_props

* cleanup total_slots return value in /props endpoint

* update /props endpoint docs with total_slots

* remove num_slots from default_generation_settings_for_props

* update /props endpoint section

1 files changed, 2 insertions, 2 deletions

diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 9481ce6b..eceda30d 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -432,7 +432,6 @@ struct llama_server_context
         }
 
         default_generation_settings_for_props = get_formated_generation(slots.front());
-        default_generation_settings_for_props["num_slots"] = params.n_parallel;
         default_generation_settings_for_props["seed"] = -1;
 
         batch = llama_batch_init(n_ctx, 0, params.n_parallel);
@@ -2639,7 +2638,8 @@ int main(int argc, char **argv)
                 json data = {
                     { "user_name",      llama.name_user.c_str() },
                     { "assistant_name", llama.name_assistant.c_str() },
-                    { "default_generation_settings", llama.default_generation_settings_for_props }
+                    { "default_generation_settings", llama.default_generation_settings_for_props },
+                    { "total_slots",    llama.params.n_parallel }
                 };
                 res.set_content(data.dump(), "application/json; charset=utf-8");
             });