[Bug] mmdeploy如何手动释放显存占用?

[liuky74]

Checklist

• I have searched related issues but cannot get the expected help.
• 2. I have read the FAQ documentation but cannot get the expected help.
• 3. The bug has not been fixed in the latest version.

Describe the bug

我的项目是基于mmdeploy-runtime进行部署的后端为使用mmdeploy转换的TensorRT模型, 项目存在多个模型, 并需要根据需求切换模型, 考虑到显存问题, 我查阅了资料, 但是没有找到类似torch.empty_cache()或paddle.clear_intermediate_tensor() + self.predictor.try_shrink_memory()手动释放显存占用得方法, 请问官方能否提供一下类似的方法?

Reproduction

无

Environment

无

Error traceback

无