cargo fmt

router/client/src/client.rs

@@ -150,7 +150,11 @@ impl Client {
         };
 
         let max_new_tokens = max_total_tokens - max_input_length;
-        let request = tonic::Request::new(WarmupRequest { batch: Some(batch), max_new_tokens }).inject_context();
+        let request = tonic::Request::new(WarmupRequest {
+            batch: Some(batch),
+            max_new_tokens,
+        })
+        .inject_context();
         let response = self.stub.warmup(request).await?.into_inner();
         Ok(response.max_supported_total_tokens)
     }

router/client/src/sharded_client.rs

@@ -100,7 +100,9 @@ impl ShardedClient {
         let futures: Vec<_> = self
             .clients
             .iter_mut()
-            .map(|client| Box::pin(client.warmup(max_input_length, max_prefill_tokens, max_total_tokens)))
+            .map(|client| {
+                Box::pin(client.warmup(max_input_length, max_prefill_tokens, max_total_tokens))
+            })
             .collect();
         // Take the minimum value
         let results = join_all(futures)

router/src/main.rs

@@ -295,7 +295,11 @@ async fn main() -> Result<(), RouterError> {
     // Warmup model
     tracing::info!("Warming up model");
     let max_supported_batch_total_tokens = match sharded_client
-        .warmup(max_input_length as u32, max_batch_prefill_tokens, max_total_tokens as u32)
+        .warmup(
+            max_input_length as u32,
+            max_batch_prefill_tokens,
+            max_total_tokens as u32,
+        )
         .await
         .map_err(RouterError::Warmup)?
     {