Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings
This repository was archived by the owner on Jul 4, 2025. It is now read-only.

Commit a90a5e8

Browse files
vansangpfievsangjanai
andauthored
fix: check model is loaded before starting (#2206)
* fix: check model is loaded before starting * chore: e2e test --------- Co-authored-by: sangjanai <sang@jan.ai>
1 parent f192287 commit a90a5e8

File tree

5 files changed

+32
-8
lines changed

5 files changed

+32
-8
lines changed

‎engine/config/yaml_config.cc‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -48,7 +48,7 @@ void YamlHandler::ReadYamlFile(const std::string& file_path) {
4848
if (!yaml_node_["mmproj"]) {
4949
auto s = nomalize_path(file_path);
5050
auto abs_path = s.substr(0, s.find_last_of('/')) + "/mmproj.gguf";
51-
CTL_DBG("mmproj: " << abs_path);
51+
CTL_TRC("mmproj: " << abs_path);
5252
auto rel_path = fmu::ToRelativeCortexDataPath(fs::path(abs_path));
5353
if (std::filesystem::exists(abs_path)) {
5454
yaml_node_["mmproj"] = rel_path.string();

‎engine/e2e-test/cli/engines/test_cli_engine_uninstall.py‎

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -24,7 +24,10 @@ def setup_and_teardown(self):
2424

2525
@pytest.mark.asyncio
2626
async def test_engines_uninstall_llamacpp_should_be_successfully(self):
27-
response = requests.post("http://localhost:3928/v1/engines/llama-cpp/install")
27+
data = {"version": "b5371"}
28+
response = requests.post(
29+
"http://localhost:3928/v1/engines/llama-cpp/install", json=data
30+
)
2831
await wait_for_websocket_download_success_event(timeout=None)
2932
exit_code, output, error = run(
3033
"Uninstall engine", ["engines", "uninstall", "llama-cpp"]

‎engine/e2e-test/cli/model/test_cli_model.py‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -36,6 +36,7 @@ def setup_and_teardown(self):
3636
run("Delete model", ["models", "delete", "tinyllama:1b"])
3737
stop_server()
3838

39+
@pytest.mark.skipif(platform.system() == "Windows", reason="Skip test for Windows")
3940
def test_model_pull_with_direct_url_should_be_success(self):
4041
exit_code, output, error = run(
4142
"Pull model",

‎engine/extensions/local-engine/local_engine.cc‎

Lines changed: 25 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -80,6 +80,11 @@ std::vector<std::string> ConvertJsonToParamsVector(const Json::Value& root) {
8080
res.push_back("--no-mmap");
8181
}
8282
continue;
83+
} else if (member == "ignore_eos") {
84+
if (root[member].asBool()) {
85+
res.push_back("--ignore_eos");
86+
}
87+
continue;
8388
}
8489

8590
res.push_back("--" + member);
@@ -502,6 +507,23 @@ void LocalEngine::HandleEmbedding(std::shared_ptr<Json::Value> json_body,
502507

503508
void LocalEngine::LoadModel(std::shared_ptr<Json::Value> json_body,
504509
http_callback&& callback) {
510+
auto model_id = json_body->get("model", "").asString();
511+
if (model_id.empty()) {
512+
CTL_WRN("Model is empty");
513+
}
514+
if (server_map_.find(model_id) != server_map_.end()) {
515+
CTL_INF("Model " << model_id << " is already loaded");
516+
Json::Value error;
517+
error["error"] = "Model " + model_id + " is already loaded";
518+
Json::Value status;
519+
status["is_done"] = true;
520+
status["has_error"] = true;
521+
status["is_stream"] = false;
522+
status["status_code"] = 409;
523+
callback(std::move(status), std::move(error));
524+
return;
525+
}
526+
505527
CTL_INF("Start loading model");
506528
auto wait_for_server_up = [this](const std::string& model,
507529
const std::string& host, int port) {
@@ -524,10 +546,7 @@ void LocalEngine::LoadModel(std::shared_ptr<Json::Value> json_body,
524546
};
525547

526548
LOG_DEBUG << "Start to spawn llama-server";
527-
auto model_id = json_body->get("model", "").asString();
528-
if (model_id.empty()) {
529-
CTL_WRN("Model is empty");
530-
}
549+
531550
server_map_[model_id].host = "127.0.0.1";
532551
server_map_[model_id].port = GenerateRandomInteger(39400, 39999);
533552
auto& s = server_map_[model_id];
@@ -545,6 +564,8 @@ void LocalEngine::LoadModel(std::shared_ptr<Json::Value> json_body,
545564
params.push_back("--pooling");
546565
params.push_back("mean");
547566

567+
params.push_back("--jinja");
568+
548569
std::vector<std::string> v;
549570
v.reserve(params.size() + 1);
550571
auto engine_dir = engine_service_.GetEngineDirPath(kLlamaRepo);

‎engine/services/model_source_service.cc‎

Lines changed: 1 addition & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -433,8 +433,7 @@ cpp::result<bool, std::string> ModelSourceService::AddCortexsoRepo(
433433

434434
auto author = hub_author;
435435
auto model_author = hu::GetModelAuthorCortexsoHub(model_name);
436-
if (auto model_author = hu::GetModelAuthorCortexsoHub(model_name);
437-
model_author.has_value() && !model_author.value().empty()) {
436+
if (model_author.has_value() && !model_author.value().empty()) {
438437
author = model_author.value();
439438
}
440439

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /