style: format Rust workspace

crates/xserv-model/src/bin/bench-gpt2.rs

@@ -1,7 +1,7 @@
 use std::path::PathBuf;
 use std::time::Instant;
-use xserv_model::gpt2::{sample_greedy, KVCache};
-use xserv_model::{loader, GPT2, ModelConfig};
+use xserv_model::gpt2::{KVCache, sample_greedy};
+use xserv_model::{GPT2, ModelConfig, loader};
 use xserv_tensor::Device;
 use xserv_tokenizer::Tokenizer;
 
@@ -104,9 +104,15 @@ fn main() {
 
         let tbt_us = if !token_times_us.is_empty() {
             token_times_us.iter().sum::<u128>() / token_times_us.len() as u128
-        } else { 0 };
+        } else {
+            0
+        };
         let total_gen_us: u128 = ttft_us + token_times_us.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('\\', "\\\\")
@@ -124,11 +130,16 @@ 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!();
+        }
 
         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,
             &generated_text.replace('\n', " ")[..generated_text.len().min(60)]
@@ -138,12 +149,18 @@ fn main() {
 }
 
 fn generate_with_cache(
-    model: &GPT2, config: &ModelConfig, tokenizer: &Tokenizer,
-    input_ids: &[u32], gen_tokens: usize,
+    model: &GPT2,
+    config: &ModelConfig,
+    tokenizer: &Tokenizer,
+    input_ids: &[u32],
+    gen_tokens: usize,
 ) -> (Vec<u32>, u128, Vec<u128>) {
     let mut cache = KVCache::new(
-        config.num_layers(), config.num_heads(), config.head_dim(),
-        xserv_tensor::DType::F32, Device::Cuda(0),
+        config.num_layers(),
+        config.num_heads(),
+        config.head_dim(),
+        xserv_tensor::DType::F32,
+        Device::Cuda(0),
     );
 
     // Prefill
@@ -163,15 +180,19 @@ fn generate_with_cache(
         let next = sample_greedy(&logits);
         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;
+        }
     }
 
     (generated, ttft_us, token_times)
 }
 
 fn generate_no_cache(
-    model: &GPT2, tokenizer: &Tokenizer,
-    input_ids: &[u32], gen_tokens: usize,
+    model: &GPT2,
+    tokenizer: &Tokenizer,
+    input_ids: &[u32],
+    gen_tokens: usize,
 ) -> (Vec<u32>, u128, Vec<u128>) {
     let mut all_ids = input_ids.to_vec();
 
@@ -191,7 +212,9 @@ fn generate_no_cache(
         token_times.push(t_start.elapsed().as_micros());
         all_ids.push(next);
         generated.push(next);
-        if tokenizer.eos_token_id() == Some(next) { break; }
+        if tokenizer.eos_token_id() == Some(next) {
+            break;
+        }
     }
 
     (generated, ttft_us, token_times)