tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 20:05:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : update readme + return json for "meta" field

Browse Source
This commit is contained in:
Georgi Gerganov
2025-05-14 15:30:12 +03:00
parent 6190e1c1c9
commit 237acc7cd5
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/README.md
View File

@ -1040,7 +1040,7 @@ To know the `id` of the adapter, use GET `/lora-adapters`
Returns information about the loaded model. See [OpenAI Models API documentation](https://platform.openai.com/docs/api-reference/models). Returns information about the loaded model. See [OpenAI Models API documentation](https://platform.openai.com/docs/api-reference/models).
The returned list always has one single element. The returned list always has one single element. The `meta` field can be `null` (for example, while the model is still loading).
By default, model `id` field is the path to model file, specified via `-m`. You can set a custom value for model `id` field via `--alias` argument. For example, `--alias gpt-4o-mini`. By default, model `id` field is the path to model file, specified via `-m`. You can set a custom value for model `id` field via `--alias` argument. For example, `--alias gpt-4o-mini`.

2
tools/server/server.cpp
View File

@ -4368,7 +4368,7 @@ int main(int argc, char ** argv) {
const auto handle_models = [&params, &ctx_server, &state, &res_ok](const httplib::Request &, httplib::Response & res) { const auto handle_models = [&params, &ctx_server, &state, &res_ok](const httplib::Request &, httplib::Response & res) {
server_state current_state = state.load(); server_state current_state = state.load();
std::string model_meta; json model_meta = nullptr;
if (current_state == SERVER_STATE_READY) { if (current_state == SERVER_STATE_READY) {
model_meta = ctx_server.model_meta(); model_meta = ctx_server.model_meta();
} }