style: format Rust workspace

crates/xserv-model/src/bin/dump-logits.rs

@@ -1,8 +1,8 @@
+use half::bf16;
 use std::path::PathBuf;
-use xserv_model::{loader, KVCache, ModelConfig, Qwen3};
+use xserv_model::{KVCache, ModelConfig, Qwen3, loader};
 use xserv_tensor::{DType, Device};
 use xserv_tokenizer::Tokenizer;
-use half::bf16;
 
 fn main() {
     let args: Vec<String> = std::env::args().collect();
@@ -20,8 +20,11 @@ fn main() {
     eprintln!("Token IDs: {token_ids:?}");
 
     let mut cache = KVCache::new(
-        config.num_layers(), config.num_kv_heads(), config.head_dim(),
-        DType::BF16, Device::Cuda(0),
+        config.num_layers(),
+        config.num_kv_heads(),
+        config.head_dim(),
+        DType::BF16,
+        Device::Cuda(0),
     );
     let logits = model.forward_with_cache(&token_ids, &mut cache);
     let logits_cpu = logits.to_device(Device::Cpu);
@@ -31,7 +34,9 @@ fn main() {
 
     // Print top-20 logits for the last position
     let last_row = &data[(seq_len - 1) * vocab_size..seq_len * vocab_size];
-    let mut indexed: Vec<(usize, f32)> = last_row.iter().enumerate()
+    let mut indexed: Vec<(usize, f32)> = last_row
+        .iter()
+        .enumerate()
         .map(|(i, v)| (i, v.to_f32()))
         .collect();
     indexed.sort_by(|a, b| b.1.partial_cmp(&a.1).unwrap());