feat: use model name as adapter id in chat endpoints

router/src/lib.rs

@@ -370,7 +370,7 @@ pub struct CompletionRequest {
     /// UNUSED
     #[schema(example = "mistralai/Mistral-7B-Instruct-v0.2")]
     /// ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.
-    pub model: String,
+    pub model: Option<String>,
 
     /// The prompt to generate completions for.
     #[schema(example = "What is Deep Learning?")]
@@ -706,7 +706,7 @@ impl ChatCompletionChunk {
 pub(crate) struct ChatRequest {
     #[schema(example = "mistralai/Mistral-7B-Instruct-v0.2")]
     /// [UNUSED] ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.
-    pub model: String,
+    pub model: Option<String>,
 
     /// A list of messages comprising the conversation so far.
     #[schema(example = "[{\"role\": \"user\", \"content\": \"What is Deep Learning?\"}]")]

router/src/server.rs

@@ -606,6 +606,7 @@ async fn completions(
     metrics::increment_counter!("tgi_request_count");
 
     let CompletionRequest {
+        model,
         max_tokens,
         seed,
         stop,
@@ -673,7 +674,7 @@ async fn completions(
                 seed,
                 top_n_tokens: None,
                 grammar: None,
-                ..Default::default()
+                adapter_id: model.as_ref().filter(|m| *m != "tgi").map(String::from),
             },
         })
         .collect();
@@ -1011,6 +1012,7 @@ async fn chat_completions(
     let span = tracing::Span::current();
     metrics::increment_counter!("tgi_request_count");
     let ChatRequest {
+        model,
         logprobs,
         max_tokens,
         messages,
@@ -1116,7 +1118,7 @@ async fn chat_completions(
             seed,
             top_n_tokens: req.top_logprobs,
             grammar,
-            ..Default::default()
+            adapter_id: model.filter(|m| *m != "tgi").map(String::from),
         },
     };