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

server: health:

Browse source 
* include_slots only if slots_endpoint
    * fix compile warning task.target_id not initialized.
This commit is contained in:
Pierrick HYMBERT 2024-02-21 14:19:18 +01:00
parent 87ceb1a42b
commit d73456ac59
2 changed files with 4 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/server/README.md
View file

@ -140,7 +140,7 @@ node index.js
- 200 -> `{"status": "no slot available", "slots_idle": 0, "slots_processing": 32}` if no slot are currently available. - 200 -> `{"status": "no slot available", "slots_idle": 0, "slots_processing": 32}` if no slot are currently available.
- 503 -> `{"status": "no slot available", "slots_idle": 0, "slots_processing": 32}` if the query parameter `fail_on_no_slot` is provided and no slot are currently available. - 503 -> `{"status": "no slot available", "slots_idle": 0, "slots_processing": 32}` if the query parameter `fail_on_no_slot` is provided and no slot are currently available.
If the query parameter `include_slots` is passed, `slots` field will contain internal slots data. If the query parameter `include_slots` is passed, `slots` field will contain internal slots data except if `--slots-endpoint-disable` is set.
- **POST** `/completion`: Given a `prompt`, it returns the predicted completion. - **POST** `/completion`: Given a `prompt`, it returns the predicted completion.

4
examples/server/server.cpp
View file

@ -2601,6 +2601,7 @@ int main(int argc, char **argv)
task_server task; task_server task;
task.id = llama.queue_tasks.get_new_id(); task.id = llama.queue_tasks.get_new_id();
task.type = TASK_TYPE_SLOTS_DATA; task.type = TASK_TYPE_SLOTS_DATA;
task.target_id = -1;
llama.queue_results.add_waiting_task_id(task.id); llama.queue_results.add_waiting_task_id(task.id);
llama.queue_tasks.post(task); llama.queue_tasks.post(task);
@ -2617,7 +2618,7 @@ int main(int argc, char **argv)
{"slots_idle", n_idle_slots}, {"slots_idle", n_idle_slots},
{"slots_processing", n_processing_slots}}; {"slots_processing", n_processing_slots}};
res.status = 200; // HTTP OK res.status = 200; // HTTP OK
if (req.has_param("include_slots")) { if (sparams.slots_endpoint && req.has_param("include_slots")) {
health["slots"] = result.result_json["slots"]; health["slots"] = result.result_json["slots"];
} }
@ -2647,6 +2648,7 @@ int main(int argc, char **argv)
task_server task; task_server task;
task.id = llama.queue_tasks.get_new_id(); task.id = llama.queue_tasks.get_new_id();
task.type = TASK_TYPE_SLOTS_DATA; task.type = TASK_TYPE_SLOTS_DATA;
task.target_id = -1;
llama.queue_results.add_waiting_task_id(task.id); llama.queue_results.add_waiting_task_id(task.id);
llama.queue_tasks.post(task); llama.queue_tasks.post(task);