x

scripts/start_vllm.py

@@ -137,8 +137,8 @@ def nuke_vllm_cache():
         except Exception as e:
             print(f" Failed: {e}")
 
-def configure_and_launch(model_idx, gpu_count):
-    print(f"DEBUG: configure_and_launch called with model_idx={model_idx}, gpu_count={gpu_count}")
+def configure_and_launch(model_idx, gpu_count, use_default=False):
+    print(f"DEBUG: configure_and_launch called with model_idx={model_idx}, gpu_count={gpu_count}, use_default={use_default}")
     model_id = MODELS_TO_RUN[model_idx]
     config = MODEL_TABLE[model_id]
     print(f"DEBUG: model_id={model_id}")
@@ -215,6 +215,15 @@ def configure_and_launch(model_idx, gpu_count):
     
     name = model_id.split("/")[-1]
     
+    # If use_default is True, skip interactive menu and launch directly
+    if use_default:
+        print(f"DEBUG: use_default=True, skipping interactive menu")
+        print(f"DEBUG: Using default config: TP={current_tp}, Seqs={current_seqs}, Ctx={current_ctx}")
+        # Jump directly to launch
+        launch_server = True
+    else:
+        launch_server = False
+    
     while True:
         cache_status = "YES" if clear_cache else "NO"
         eager_status = "YES" if use_eager else "NO"
@@ -314,6 +323,10 @@ def configure_and_launch(model_idx, gpu_count):
              
         elif choice == "8":
             # Launch
+            launch_server = True
+            break
+        
+        if launch_server:
             break
             
     # Build Command
@@ -385,7 +398,7 @@ def main():
         try:
             default_idx = MODELS_TO_RUN.index(DEFAULT_MODEL)
             print(f"Using default model: {DEFAULT_MODEL}")
-            configure_and_launch(default_idx, gpu_count)
+            configure_and_launch(default_idx, gpu_count, use_default=True)
         except ValueError:
             print(f"Error: Default model {DEFAULT_MODEL} not found in configuration")
             sys.exit(1)