ChatGLM3-6B独立部署提供HTTP服务failed to open nvrtc-builtins64_121.dll

Hugo Lei2024-03-17 10:31

背景

我在本地windoes部署ChatGLM3-bB，且希望部署后能提供HTTP server的能力。

模型部署且启动是成功了，但是在访问生成接口**/v1/chat/completions**时报错failed to open nvrtc-builtins64_121.dll。

问题详细描述

找不到nvrtc-builtins64_121.dll

RuntimeError: nvrtc: error: failed to open nvrtc-builtins64_121.dll.

Make sure that nvrtc-builtins64_121.dll is installed correctly.

bash 复制代码

  File "D:\ProgramData\Miniconda3\envs\chatglm\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "D:\ProgramData\Miniconda3\envs\chatglm\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Administrator\.cache\huggingface\modules\transformers_modules\chatglm3-6b\modeling_chatglm.py", line 408, in forward
    query_layer = apply_rotary_pos_emb(query_layer, rotary_pos_emb)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript (most recent call last):
RuntimeError: nvrtc: error: failed to open nvrtc-builtins64_121.dll.
  Make sure that nvrtc-builtins64_121.dll is installed correctly.

github上也有人报了这个问题

解决方案

原因：pytorch和cuda版本不匹配导致的

pytorch安装时，对应的CUDA12.1

但我本地之前安装的是CUDA12.4

因此找不到12.1版本的nvrtc-builtins64_121

方案：安装多版本CUDA，再安装一个CUDA12.1