refactor: move libs to lib dir

Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>

llm/rust/triton-llm/src/protocols/openai/completions.rs → lib/llm/src/protocols/openai/completions.rs

@@ -32,7 +32,7 @@ use super::{
     MAX_TOP_P, MIN_FREQUENCY_PENALTY, MIN_PRESENCE_PENALTY, MIN_TEMPERATURE, MIN_TOP_P,
 };
 
-use triton_distributed::protocols::annotated::AnnotationsProvider;
+use triton_distributed_runtime::protocols::annotated::AnnotationsProvider;
 
 /// Legacy OpenAI CompletionRequest
 ///
@@ -176,7 +176,7 @@ pub struct CompletionRequest {
     /// in the vocabulary of the model.
     ///
     /// ```rust
-    /// use triton_llm::protocols::openai::completions::CompletionRequest;
+    /// use triton_distributed_llm::protocols::openai::completions::CompletionRequest;
     ///
     /// let request = CompletionRequest::builder()
     ///     .prompt("What is the meaning of life?")
@@ -243,7 +243,7 @@ impl CompletionRequestBuilder {
     /// Builds and validates the CompletionRequest
     ///
     /// ```rust
-    /// use triton_llm::protocols::openai::completions::CompletionRequest;
+    /// use triton_distributed_llm::protocols::openai::completions::CompletionRequest;
     ///
     /// let request = CompletionRequest::builder()
     ///     .model("mixtral-8x7b-instruct-v0.1")

llm/rust/triton-llm/src/types.rs → lib/llm/src/types.rs

@@ -19,7 +19,7 @@ pub use protocols::{Annotated, TokenIdType};
 
 pub mod openai {
     use super::*;
-    use triton_distributed::pipeline::{ServerStreamingEngine, UnaryEngine};
+    use triton_distributed_runtime::pipeline::{ServerStreamingEngine, UnaryEngine};
 
     pub mod completions {
         use super::*;

llm/rust/triton-llm/tests/aggregators.rs → lib/llm/tests/aggregators.rs

@@ -14,7 +14,7 @@
 // limitations under the License.
 
 use futures::StreamExt;
-use triton_llm::protocols::{
+use triton_distributed_llm::protocols::{
     codec::{create_message_stream, Message, SseCodecError},
     openai::{chat_completions::ChatCompletionResponse, completions::CompletionResponse},
     ContentProvider, DataStream,