运行demo.py后报错：“RuntimeError: (NotFound) The kernel with key (GPU, NCHW, float16) of kernel `multinomial` is not registered and fail to fallback to CPU one.”

[cc8887]

在百度的云环境（BML CoderLab）中运行报错： （demo.py本地加入注释，所以行数显示不对，路径为get_knowledge_based_answer->knowledge_chainknowledge_chain） raceback (most recent call last): File "/home/aistudio/LangChain-ChatGLM-Webui/paddlepaddle/demo.py", line 123, in resp = get_knowledge_based_answer( File "/home/aistudio/LangChain-ChatGLM-Webui/paddlepaddle/demo.py", line 77, in get_knowledge_based_answer result = knowledge_chain({"query": query}) File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/base.py", line 116, in call raise e File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/base.py", line 113, in call outputs = self._call(inputs) File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/retrieval_qa/base.py", line 110, in _call answer = self.combine_documents_chain.run( File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/base.py", line 216, in run return self(kwargs)[self.output_keys[0]] File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/base.py", line 116, in call raise e File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/base.py", line 113, in call outputs = self._call(inputs) File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/combine_documents/base.py", line 75, in _call output, extra_return_dict = self.combine_docs(docs, other_keys) File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/combine_documents/stuff.py", line 83, in combine_docs return self.llm_chain.predict(inputs), {} File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/llm.py", line 151, in predict return self(kwargs)[self.output_key] File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/base.py", line 116, in call raise e File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/base.py", line 113, in call outputs = self._call(inputs) File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/llm.py", line 57, in _call return self.apply([inputs])[0] File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/llm.py", line 118, in apply response = self.generate(input_list) File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/chains/llm.py", line 62, in generate return self.llm.generate_prompt(prompts, stop) File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/llms/base.py", line 107, in generate_prompt return self.generate(prompt_strings, stop=stop) File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/llms/base.py", line 140, in generate raise e File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/llms/base.py", line 137, in generate output = self._generate(prompts, stop=stop) File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/langchain/llms/base.py", line 324, in _generate text = self._call(prompt, stop=stop) File "/home/aistudio/LangChain-ChatGLM-Webui/paddlepaddle/chatllm.py", line 31, in _call results = chatbot(prompt_list) File "/home/aistudio/.data/webide/pip/lib/python3.9/site-packages/paddlenlp/taskflow/taskflow.py", line 802, in call results = self.task_instance(inputs) File "/home/aistudio/.data/webide/pip/lib/python3.9/site-packages/paddlenlp/taskflow/task.py", line 522, in call outputs = self._run_model(inputs) File "/home/aistudio/.data/webide/pip/lib/python3.9/site-packages/paddlenlp/taskflow/text2text_generation.py", line 196, in _run_model result = self._model.generate( File "", line 2, in generate File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/paddle/fluid/dygraph/base.py", line 375, in _decorate_function return func(*args, **kwargs) File "/home/aistudio/.data/webide/pip/lib/python3.9/site-packages/paddlenlp/transformers/generation_utils.py", line 947, in generate return self.sample( File "/home/aistudio/.data/webide/pip/lib/python3.9/site-packages/paddlenlp/transformers/generation_utils.py", line 1136, in sample next_tokens = paddle.multinomial(probs) File "/opt/conda/envs/python35-paddle120-env/lib/python3.9/site-packages/paddle/tensor/random.py", line 186, in multinomial return _C_ops.multinomial(x, num_samples, replacement) RuntimeError: (NotFound) The kernel with key (GPU, NCHW, float16) of kernel multinomial is not registered and fail to fallback to CPU one. [Hint: Expected kernel_iter != iter->second.end(), but received kernel_iter == iter->second.end().] (at /paddle/paddle/phi/core/kernel_factory.cc:168)

[thomas-yanxin]

看一下paddle的版本以及paddlenlp的版本 可参考：https://aistudio.baidu.com/aistudio/projectdetail/6195067