Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 13:28:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

server : enhanced health endpoint (#5548)

Browse Source 
* server: enrich health endpoint with available slots, return 503 if not slots are available

* server: document new status no slot available in the README.md
This commit is contained in:
Pierrick Hymbert 2024-02-18 17:31:28 +01:00 committed by GitHub
parent 36376abe05
commit e75c6279d1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 30 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
examples/server/README.md
View File

@ -136,6 +136,7 @@ node index.js
- `{"status": "loading model"}` if the model is still being loaded.
- `{"status": "error"}` if the model failed to load.
- `{"status": "ok"}` if the model is successfully loaded and the server is ready for further requests mentioned below.
- `{"status": "no slot available", "slots_idle": 0, "slots_processing": 32}` if no slot are currently available
- **POST** `/completion`: Given a `prompt`, it returns the predicted completion.

31
examples/server/server.cpp
View File

@ -2578,8 +2578,35 @@ int main(int argc, char **argv)
server_state current_state = state.load();
switch(current_state) {
case SERVER_STATE_READY:
res.set_content(R"({"status": "ok"})", "application/json");
res.status = 200; // HTTP OK
if (llama.all_slots_are_idle) {
res.set_content(R"({"status": "ok"})", "application/json");
res.status = 200; // HTTP OK
} else {
int available_slots = 0;
int processing_slots = 0;
for (llama_client_slot & slot : llama.slots) {
if (slot.available()) {
available_slots++;
} else {
processing_slots++;
}
}
if (available_slots > 0) {
json health = {
{"status", "ok"},
{"slots_idle", available_slots},
{"slots_processing", processing_slots}};
res.set_content(health.dump(), "application/json");
res.status = 200; // HTTP OK
} else {
json health = {
{"status", "no slot available"},
{"slots_idle", available_slots},
{"slots_processing", processing_slots}};
res.set_content(health.dump(), "application/json");
res.status = 503; // HTTP Service Unavailable
}
}
break;
case SERVER_STATE_LOADING_MODEL:
res.set_content(R"({"status": "loading model"})", "application/json");