style: format Rust workspace

crates/xserv-model/src/bin/bench-qwen3.rs

@@ -1,7 +1,7 @@
 use std::path::PathBuf;
 use std::time::Instant;
 use xserv_model::qwen3::sample_greedy;
-use xserv_model::{loader, DecodeGraphState, GpuKVCache, ModelConfig, Qwen3};
+use xserv_model::{DecodeGraphState, GpuKVCache, ModelConfig, Qwen3, loader};
 use xserv_tensor::{DType, Device};
 use xserv_tokenizer::Tokenizer;
 
@@ -139,18 +139,35 @@ fn main() {
                 } else {
                     // Replay captured graphs
                     let pos = cache.seq_len() as u32;
-                    graph.execute(last, pos, &mut cache, &layer_ptrs, embed, config.vocab_size as i32, config.hidden() as i32);
+                    graph.execute(
+                        last,
+                        pos,
+                        &mut cache,
+                        &layer_ptrs,
+                        embed,
+                        config.vocab_size as i32,
+                        config.hidden() as i32,
+                    );
                     cache.advance_seq_len(1);
                     // Read logits from graph buffer
                     let vocab_size = config.vocab_size;
                     let mut logits_bytes = vec![0u8; vocab_size * 2];
-                    graph.logits_buffer().copy_to_host(&mut logits_bytes).unwrap();
+                    graph
+                        .logits_buffer()
+                        .copy_to_host(&mut logits_bytes)
+                        .unwrap();
                     let logits_data: &[half::bf16] = unsafe {
-                        std::slice::from_raw_parts(logits_bytes.as_ptr() as *const half::bf16, vocab_size)
+                        std::slice::from_raw_parts(
+                            logits_bytes.as_ptr() as *const half::bf16,
+                            vocab_size,
+                        )
                     };
-                    logits_data.iter().enumerate()
+                    logits_data
+                        .iter()
+                        .enumerate()
                         .max_by(|a, b| a.1.to_f32().partial_cmp(&b.1.to_f32()).unwrap())
-                        .map(|(idx, _)| idx as u32).unwrap()
+                        .map(|(idx, _)| idx as u32)
+                        .unwrap()
                 }
             } else {
                 let logits = model.forward_gpu_cache(&[last], &mut cache);
@@ -159,16 +176,24 @@ fn main() {
 
             token_times.push(t_start.elapsed().as_micros());
             generated.push(next);
-            if tokenizer.eos_token_id() == Some(next) { break; }
+            if tokenizer.eos_token_id() == Some(next) {
+                break;
+            }
         }
 
         let num_generated = generated.len();
         let generated_text = tokenizer.decode(&generated);
         let tbt_us = if !token_times.is_empty() {
             token_times.iter().sum::<u128>() / token_times.len() as u128
-        } else { 0 };
+        } else {
+            0
+        };
         let total_gen_us: u128 = ttft_us + token_times.iter().sum::<u128>();
-        let tpot_us = if num_generated > 0 { total_gen_us / num_generated as u128 } else { 0 };
+        let tpot_us = if num_generated > 0 {
+            total_gen_us / num_generated as u128
+        } else {
+            0
+        };
 
         let gen_text_escaped = generated_text
             .replace('\\', "\\\\")
@@ -186,13 +211,18 @@ fn main() {
         print!("\"ttft_us\": {ttft_us}, ");
         print!("\"tbt_us\": {tbt_us}, ");
         print!("\"tpot_us\": {tpot_us}}}");
-        if i < prompts.len() - 1 { println!(","); } else { println!(); }
+        if i < prompts.len() - 1 {
+            println!(",");
+        } else {
+            println!();
+        }
 
         let display_text = generated_text.replace('\n', " ");
         let truncated: String = display_text.chars().take(60).collect();
         eprintln!(
             "[{}/{}] input={input_len}tok gen={num_generated}tok ttft={:.1}ms tbt={:.1}ms | {}",
-            i + 1, prompts.len(),
+            i + 1,
+            prompts.len(),
             ttft_us as f64 / 1000.0,
             tbt_us as f64 / 1000.0,
             truncated