vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

add "model_path" to /props

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-12-07 20:05:04 +01:00
parent 65d2e6d675
commit 1949f68f4e
2 changed files with 5 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
examples/server/server.cpp
View file

@ -801,7 +801,8 @@ struct server_task_result_metrics : server_task_result {
uint64_t n_decode_total = 0;
uint64_t n_busy_slots_total = 0;
// TODO: get rid of this json object and use to_json() instead
// while we can also use std::vector<server_slot> this requires copying the slot object which can be quite messy
// therefore, we use json to temporarily store the slot.to_json() result
json slots_data = json::array();
virtual json to_json() override {
@ -3326,9 +3327,11 @@ int main(int argc, char ** argv) {
};
const auto handle_props = [&ctx_server, &res_ok](const httplib::Request &, httplib::Response & res) {
// this endpoint is publicly available, please only return what is safe to be exposed
json data = {
{ "default_generation_settings", ctx_server.default_generation_settings_for_props },
{ "total_slots", ctx_server.params_base.n_parallel },
{ "model_path", ctx_server.params_base.model },
{ "chat_template", llama_get_chat_template(ctx_server.model) },
};

1
examples/server/tests/unit/test_basic.py
View file

@ -22,6 +22,7 @@ def test_server_props():
server.start()
res = server.make_request("GET", "/props")
assert res.status_code == 200
assert ".gguf" in res.body["model_path"]
assert res.body["total_slots"] == server.n_slots
default_val = res.body["default_generation_settings"]
assert server.n_ctx is not None and server.n_slots is not None