Thanks to visit codestin.com
Credit goes to github.com

Skip to content
This repository was archived by the owner on Jul 4, 2025. It is now read-only.

fix: use updated configuration for remote model when reload #1972

Merged
merged 1 commit into from
Feb 15, 2025
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions engine/services/inference_service.cc
Original file line number Diff line number Diff line change
Expand Up @@ -24,8 +24,12 @@ cpp::result<void, InferResult> InferenceService::HandleChatCompletion(
auto status = std::get<0>(ir)["status_code"].asInt();
if (status != drogon::k200OK) {
CTL_INF("Model is not loaded, start loading it: " << model_id);
auto res = LoadModel(saved_models_.at(model_id));
// ignore return result
// For remote engine, we use the updated configuration
if (engine_service_->IsRemoteEngine(engine_type)) {
(void)model_service_.lock()->StartModel(model_id, {}, false);
} else {
(void)LoadModel(saved_models_.at(model_id));
}
}
}

Expand Down
Loading