CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : health endpoint configurable failure on no slot (#5594)

Browse Source
This commit is contained in:
Pierrick Hymbert
2024-02-20 08:48:19 +01:00
committed by GitHub
parent b9111bd209
commit c0a8c6db37
2 changed files with 31 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/server/README.md
View File

@@ -134,10 +134,11 @@ node index.js
## API Endpoints
- **GET** `/health`: Returns the current state of the server:
- `{"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
- 503 -> `{"status": "loading model"}` if the model is still being loaded.
- 500 -> `{"status": "error"}` if the model failed to load.
- 200 -> `{"status": "ok", "slots_idle": 1, "slots_processing": 2 }` if the model is successfully loaded and the server is ready for further requests mentioned below.
- 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.
- **POST** `/completion`: Given a `prompt`, it returns the predicted completion.

52
examples/server/server.cpp
View File

@@ -2582,40 +2582,40 @@ int main(int argc, char **argv)
res.set_header("Access-Control-Allow-Headers", "*");
});
svr.Get("/health", [&](const httplib::Request&, httplib::Response& res) {
svr.Get("/health", [&](const httplib::Request& req, httplib::Response& res) {
server_state current_state = state.load();
switch(current_state) {
case SERVER_STATE_READY:
if (llama.all_slots_are_idle) {
res.set_content(R"({"status": "ok"})", "application/json");
case SERVER_STATE_READY: {
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 {
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");
json health = {
{"status", "no slot available"},
{"slots_idle", available_slots},
{"slots_processing", processing_slots}};
res.set_content(health.dump(), "application/json");
if (req.has_param("fail_on_no_slot")) {
res.status = 503; // HTTP Service Unavailable
} else {
res.status = 200; // HTTP OK
}
}
break;
}
case SERVER_STATE_LOADING_MODEL:
res.set_content(R"({"status": "loading model"})", "application/json");
res.status = 503; // HTTP Service Unavailable