成功的尝试

scripts/evaluation/world_model_interaction.py

@@ -585,6 +585,11 @@ def run_inference(args: argparse.Namespace, gpu_num: int, gpu_no: int) -> None:
                    if isinstance(m, CrossAttention) and m.fuse_kv())
     print(f"    ✓ KV fused: {kv_count} attention layers")
 
+    # Load TRT backbone if engine exists
+    trt_engine_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), '..', '..', 'trt_engines', 'video_backbone.engine')
+    if os.path.exists(trt_engine_path):
+        model.model.diffusion_model.load_trt_backbone(trt_engine_path)
+
     # Run over data
     assert (args.height % 16 == 0) and (
         args.width % 16