lint fix

python/aibrix/aibrix/gpu_optimizer/optimizer/profiling/gen_benchmark_prompt.py

@@ -1,12 +1,13 @@
+import argparse
 import json
+import os
+import threading
 import time
+from typing import Any, Dict, List, Optional, Tuple
+
 import requests
-from typing import Tuple, List, Optional, Dict, Union, Any
-from datetime import datetime
-import threading
-import argparse
 import tiktoken
-import os
+
 
 def get_tokenizer(
         pretrained_model_name_or_path: str, trust_remote_code: bool
@@ -93,7 +94,7 @@ def find_matching_prompts(self, target_input_tokens: int, min_output_tokens: int
         input_min = int(target_input_tokens * (1 - input_tolerance))
         input_max = int(target_input_tokens * (1 + input_tolerance))
 
-        print(f"Scanning trace file for candidates...")
+        print("Scanning trace file for candidates...")
         print(f"Input token range: {input_min} - {input_max}")
 
         # First pass: collect all candidates based on input length
@@ -109,7 +110,7 @@ def find_matching_prompts(self, target_input_tokens: int, min_output_tokens: int
                         input_diff = abs(input_tokens - target_input_tokens)
                         candidates.append((prompt, input_tokens, input_diff))
 
-                except (json.JSONDecodeError, Exception) as e:
+                except (json.JSONDecodeError, Exception):
                     continue
 
         # Sort candidates by input difference
@@ -212,7 +213,7 @@ def main():
     args = parse_args()
     start_time = time.time()
 
-    print(f"\nStarting prompt search with parameters:")
+    print("\nStarting prompt search with parameters:")
     print(f"Target input tokens: {args.input_tokens}")
     print(f"Minimum output tokens: {args.min_output_tokens}")
     print(f"Tolerance: {args.tolerance}")