Update app.py

app.py

@@ -49,7 +49,7 @@ class ModelManager:
             return self.models
         
         print("Iniciando carga de modelos...")
-        with ThreadPoolExecutor(max_workers=len(model_configs)) as executor:
+        with ThreadPoolExecutor() as executor:  # No hay límite de trabajadores
             futures = [executor.submit(self.load_model, config) for config in model_configs]
             models = []
             for future in tqdm(as_completed(futures), total=len(model_configs), desc="Cargando modelos", unit="modelo"):
@@ -156,7 +156,7 @@ async def generate_chat(request: ChatRequest):
     responses = []
     num_models = len(global_data['models'])
 
-    with ThreadPoolExecutor(max_workers=num_models) as executor:
+    with ThreadPoolExecutor() as executor:  # No se establece límite de concurrencia
         futures = [executor.submit(worker_function, model_data, request) for model_data in global_data['models']]
         for future in tqdm(as_completed(futures), total=num_models, desc="Generando respuestas", unit="modelo"):
             try: