mac intel 芯片运行报错 RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'

[devon-ye]

运行环境 Mac intel芯片

127.0.0.1:根据以下主题，写一篇高度凝练且全面的论文提纲：神经网络
ERROR:    Exception in ASGI application
Traceback (most recent call last):
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/uvicorn/protocols/websockets/websockets_impl.py", line 247, in run_asgi
    result = await self.app(self.scope, self.asgi_receive, self.asgi_send)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/uvicorn/middleware/proxy_headers.py", line 84, in __call__
    return await self.app(scope, receive, send)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/fastapi/applications.py", line 1106, in __call__
    await super().__call__(scope, receive, send)
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/starlette/applications.py", line 122, in __call__
    await self.middleware_stack(scope, receive, send)
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/starlette/middleware/errors.py", line 149, in __call__
    await self.app(scope, receive, send)
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/starlette/middleware/base.py", line 26, in __call__
    await self.app(scope, receive, send)
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 79, in __call__
    raise exc
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 68, in __call__
    await self.app(scope, receive, sender)
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/fastapi/middleware/asyncexitstack.py", line 20, in __call__
    raise e
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/fastapi/middleware/asyncexitstack.py", line 17, in __call__
    await self.app(scope, receive, send)
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/starlette/routing.py", line 718, in __call__
    await route.handle(scope, receive, send)
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/starlette/routing.py", line 341, in handle
    await self.app(scope, receive, send)
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/starlette/routing.py", line 82, in app
    await func(session)
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/fastapi/routing.py", line 325, in app
    await dependant.call(**values)
  File "/Users/devon/AllProjects/PythonProjects/wenda/wenda.py", line 349, in websocket_endpoint
    raise e
  File "/Users/devon/AllProjects/PythonProjects/wenda/wenda.py", line 338, in websocket_endpoint
    for response in LLM.chat_one(prompt, history_formatted, max_length, top_p, temperature, data):
  File "/Users/devon/AllProjects/PythonProjects/wenda/llms/llm_glm6b.py", line 44, in chat_one
    for response, history in model.stream_chat(tokenizer, prompt, history_formatted,
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 35, in generator_context
    response = gen.send(None)
               ^^^^^^^^^^^^^^
  File "/Users/devon/.cache/huggingface/modules/transformers_modules/local/modeling_chatglm.py", line 1072, in stream_chat
    for outputs in self.stream_generate(**inputs, past_key_values=past_key_values,
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 35, in generator_context
    response = gen.send(None)
               ^^^^^^^^^^^^^^
  File "/Users/devon/.cache/huggingface/modules/transformers_modules/local/modeling_chatglm.py", line 1159, in stream_generate
    outputs = self(
              ^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.cache/huggingface/modules/transformers_modules/local/modeling_chatglm.py", line 937, in forward
    transformer_outputs = self.transformer(
                          ^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.cache/huggingface/modules/transformers_modules/local/modeling_chatglm.py", line 830, in forward
    hidden_states, presents, all_hidden_states, all_self_attentions = self.encoder(
                                                                      ^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.cache/huggingface/modules/transformers_modules/local/modeling_chatglm.py", line 640, in forward
    layer_ret = layer(
                ^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.cache/huggingface/modules/transformers_modules/local/modeling_chatglm.py", line 544, in forward
    attention_output, kv_cache = self.self_attention(
                                 ^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.cache/huggingface/modules/transformers_modules/local/modeling_chatglm.py", line 376, in forward
    mixed_x_layer = self.query_key_value(hidden_states)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/devon/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torch/nn/modules/linear.py", line 114, in forward
    return F.linear(input, self.weight, self.bias)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: "addmm_impl_cpu_" not implemented for 'Half'