NotImplementedError: Cannot copy out of meta tensor; no data!,设置device_map为auto就报错了

[kkkwjr]

Traceback (most recent call last): File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/gradio/queueing.py", line 407, in call_prediction output = await route_utils.call_process_api( File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/gradio/route_utils.py", line 226, in call_process_api output = await app.get_blocks().process_api( File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/gradio/blocks.py", line 1550, in process_api result = await self.call_function( File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/gradio/blocks.py", line 1185, in call_function prediction = await anyio.to_thread.run_sync( File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/anyio/to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 2177, in run_sync_in_worker_thread return await future File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 859, in run result = context.run(func, *args) File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/gradio/utils.py", line 661, in wrapper response = f(*args, **kwargs) File "/workspace/kkkjr/Item/MuseV/scripts/gradio/app.py", line 98, in hf_online_t2v_inference return online_t2v_inference( File "/workspace/kkkjr/Item/MuseV/scripts/gradio/gradio_text2video.py", line 882, in online_t2v_inference out_videos = sd_predictor.run_pipe_text2video( File "/workspace/kkkjr/Item/MuseV/musev/pipelines/pipeline_controlnet_predictor.py", line 692, in run_pipe_text2video out = self.pipeline( File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/workspace/kkkjr/Item/MuseV/musev/pipelines/pipeline_controlnet.py", line 1566, in call prompt_embeds = encode_weighted_prompt( File "/workspace/kkkjr/Item/MuseV/musev/utils/text_emb_util.py", line 408, in encode_weighted_prompt prompt_embeds1, negative_prompt_embeds1 = get_weighted_text_embeddings( File "/workspace/kkkjr/Item/MuseV/musev/utils/text_emb_util.py", line 317, in get_weighted_text_embeddings text_embeddings = get_unweighted_text_embeddings( File "/workspace/kkkjr/Item/MuseV/musev/utils/text_emb_util.py", line 198, in get_unweighted_text_embeddings text_embedding = pipe.text_encoder(text_input_chunk)[0] File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/accelerate/hooks.py", line 165, in new_forward output = old_forward(*args, **kwargs) File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/transformers/models/clip/modeling_clip.py", line 840, in forward return self.text_model( File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/transformers/models/clip/modeling_clip.py", line 735, in forward hidden_states = self.embeddings(input_ids=input_ids, position_ids=position_ids) File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/accelerate/hooks.py", line 160, in new_forward args, kwargs = module._hf_hook.pre_forward(module, *args, **kwargs) File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/accelerate/hooks.py", line 290, in pre_forward return send_to_device(args, self.execution_device), send_to_device( File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/accelerate/utils/operations.py", line 160, in send_to_device { File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/accelerate/utils/operations.py", line 161, in k: t if k in skip_keys else send_to_device(t, device, non_blocking=non_blocking, skip_keys=skip_keys) File "/home/wpg/anaconda3/envs/musev/lib/python3.10/site-packages/accelerate/utils/operations.py", line 167, in send_to_device return tensor.to(device, non_blocking=non_blocking) NotImplementedError: Cannot copy out of meta tensor; no data!