Add multithreaded logging infrastructure for preparation for future designs (#225)

* Update class diagrams

* Implement BoundedChannel and multithreaded logging infra

* Integrate logging channel system

* Update string concatenations to use std::format

* Add pretty print log

tooling/pipeline/src/data_generation/llama/load.cc

@@ -4,9 +4,8 @@
  * context, and resets prior resources during model initialization.
  */
 
-#include <spdlog/spdlog.h>
-
 #include <algorithm>
+#include <chrono>
 #include <stdexcept>
 #include <string>
 #include <utility>
@@ -29,8 +28,10 @@ void LlamaGenerator::Load(const std::string& model_path) {
 
   llama_model_params model_params = llama_model_default_params();
   model_params.n_gpu_layers = n_gpu_layers_;
-  LlamaGenerator::ModelHandle loaded_model(
+
+  ModelHandle loaded_model(
       llama_model_load_from_file(model_path.c_str(), model_params));
+
   if (!loaded_model) {
     throw std::runtime_error(
         "LlamaGenerator: failed to load model from path: " + model_path);
@@ -40,8 +41,9 @@ void LlamaGenerator::Load(const std::string& model_path) {
   context_params.n_ctx = n_ctx_;
   context_params.n_batch = std::min(n_ctx_, kMaxBatchSize);
 
-  LlamaGenerator::ContextHandle loaded_context(
+  ContextHandle loaded_context(
       llama_init_from_model(loaded_model.get(), context_params));
+
   if (!loaded_context) {
     throw std::runtime_error("LlamaGenerator: failed to create context");
   }
@@ -49,5 +51,10 @@ void LlamaGenerator::Load(const std::string& model_path) {
   model_ = std::move(loaded_model);
   context_ = std::move(loaded_context);
 
-  spdlog::info("[LlamaGenerator] Loaded model: {}", model_path);
+  if (logger_) {
+    logger_->Log({.level = LogLevel::Info,
+                  .phase = PipelinePhase::Startup,
+                  .message = std::format("[LlamaGenerator] Loaded model: {} ",
+                                         model_path)});
+  }
 }