Optimize Qwen3.8 inference on Apple silicon

src/engine/tokenizer.rs

@@ -62,7 +62,6 @@ struct QwenTokenizerFile {
 struct QwenAddedToken {
     id: usize,
     content: String,
-    special: bool,
 }
 
 #[derive(Deserialize)]
@@ -225,9 +224,7 @@ impl Tokenizer {
                 ));
             }
             tokens[token.id] = token.content.as_bytes().to_vec();
-            if token.special {
-                rendered_specials.push((token.content.into_bytes(), token.id as i32));
-            }
+            rendered_specials.push((token.content.into_bytes(), token.id as i32));
         }
         if tokens[..=maximum].iter().any(Vec::is_empty) {
             return Err("Qwen tokenizer token ids are not contiguous".into());