fix: Fix cargo doc warnings for lib/llm (#151)

lib/llm/src/http/service.rs

@@ -28,7 +28,7 @@
 //! TODO(): Add support for model-specific metadata and status. Status will allow us to return a 503 when the model is supposed
 //! to be ready, but there is a problem with the model.
 //!
-//! The [`service::HttpService`] can be further extended to host any [`axum::Router`] using the [`service::HttpServiceBuilder`].
+//! The [`service_v2::HttpService`] can be further extended to host any [`axum::Router`] using the [`service_v2::HttpServiceConfigBuilder`].
 
 mod openai;
 

lib/llm/src/http/service/discovery.rs

@@ -38,7 +38,7 @@ use tracing;
 pub struct ModelEntry {
     /// Public name of the model
     /// This will be used to identify the model in the HTTP service and the value used in an
-    /// an [OAI ChatRequest][crate::protocols::openai::chat_completions::ChatCompletionRequest].
+    /// an [OAI ChatRequest][crate::protocols::openai::chat_completions::NvCreateChatCompletionRequest].
     pub name: String,
 
     /// Component of the endpoint.

lib/llm/src/kv_router/protocols.rs

@@ -29,7 +29,7 @@ pub struct ForwardPassMetrics {
     pub gpu_prefix_cache_hit_rate: f32,
 }
 
-/// A [`BlockHash`] is a hash computed from the tokens_ids, extra_token_ids and the optional
+/// A [`LocalBlockHash`] is a hash computed from the tokens_ids, extra_token_ids and the optional
 /// lora_id of a block.
 #[derive(Clone, Copy, Debug, PartialEq, Eq, Hash, Ord, PartialOrd)]
 pub struct LocalBlockHash(pub u64);

lib/llm/src/preprocessor.rs

@@ -88,7 +88,7 @@ impl OpenAIPreprocessor {
         }))
     }
 
-    /// Translate a [`ChatCompletionRequest`] request to a common completion request.
+    /// Translate a [`NvCreateChatCompletionRequest`] request to a common completion request.
     /// Returns both the common completion request and a hashmap of annotations.
     ///
     /// Annotations evaluated by this method include:

lib/llm/src/protocols/openai/chat_completions/delta.rs

@@ -167,7 +167,7 @@ impl DeltaGenerator {
     }
 }
 
-/// Implements the [`DeltaGeneratorExt`] trait for [`DeltaGenerator`], allowing
+/// Implements the [`crate::protocols::openai::DeltaGeneratorExt`] trait for [`DeltaGenerator`], allowing
 /// it to transform backend responses into OpenAI-style streaming responses.
 impl crate::protocols::openai::DeltaGeneratorExt<NvCreateChatCompletionStreamResponse>
     for DeltaGenerator