feat: new router and benchmark setup

src/cluster/cluster.rs

@@ -54,7 +54,11 @@ impl Cluster {
             router,
             block_size_tokens: model.block_size_tokens,
             kv_block_bytes: model.kv_block_bytes(),
-            ttft_model: TtftModel::new(&config.hardware, &config.calibration, model.kv_block_bytes()),
+            ttft_model: TtftModel::new(
+                &config.hardware,
+                &config.calibration,
+                model.kv_block_bytes(),
+            ),
         }
     }
 
@@ -256,6 +260,8 @@ mod tests {
         let req = RequestRecord {
             req_id: 1,
             chat_id: 0,
+            parent_chat_id: -1,
+            turn: 1,
             arrival: 0.0,
             input_len: 32,
             output_len: 16,
@@ -269,7 +275,10 @@ mod tests {
             .insert_blocks(&req.hash_ids, &mut evicted);
 
         let stats = cluster.route_and_admit(&req, 0.0);
-        let pure_pcie = cluster.instances[0].links.pcie.cost(cluster.kv_block_bytes * 2);
+        let pure_pcie = cluster.instances[0]
+            .links
+            .pcie
+            .cost(cluster.kv_block_bytes * 2);
 
         assert!(stats.ready_at > pure_pcie);
     }