auto-coder icon indicating copy to clipboard operation
auto-coder copied to clipboard

Ubuntu下安装时候报错

Open sunweihunu opened this issue 1 year ago • 5 comments

auto-coder.chat

🚀 正在初始化系统... ✓ 项目初始化完成。 正在检查Ray状态... ✓ Ray已经在运行。 正在检查deepseek_chat模型可用性... ! deepseek_chat模型不可用。请选择一个提供商: 请输入您的API密钥: sk-by****************************************** 正在使用硅基流动部署deepseek_chat模型... Command Line Arguments:

command : deploy ray_address : auto num_workers : 1 worker_concurrency : 1000 gpus_per_worker : 0.0 cpus_per_worker : 0.001 model_path : pretrained_model_type: saas/openai model : deepseek_chat infer_backend : infer_params : {'saas.base_url': 'https://api.siliconflow.cn/v1', 'saas.api_key': '******', 'saas.model': 'deepseek-ai/deepseek-v2-chat'} file : None

✓ Ray is already running 2024-11-27 23:07:14,509 INFO worker.py:1634 -- Connecting to existing Ray cluster at address: 192.168.1.103:6379... 2024-11-27 23:07:14,516 INFO worker.py:1810 -- Connected to Ray cluster. View the dashboard at 127.0.0.1:8265 模型 deepseek_chat 已经部署过了 正在使用硅基流动部署deepseek_chat模型... Command Line Arguments:

command : deploy ray_address : auto num_workers : 1 worker_concurrency : 1000 gpus_per_worker : 0.0 cpus_per_worker : 0.001 model_path : pretrained_model_type: saas/openai model : deepseek_chat infer_backend : infer_params : {'saas.base_url': 'https://api.siliconflow.cn/v1', 'saas.api_key': '******', 'saas.model': 'deepseek-ai/deepseek-v2-chat'} file : None

✓ Ray is already running 2024-11-27 23:07:14,509 INFO worker.py:1634 -- Connecting to existing Ray cluster at address: 192.168.1.103:6379... 2024-11-27 23:07:14,516 INFO worker.py:1810 -- Connected to Ray cluster. View the dashboard at 127.0.0.1:8265 模型 deepseek_chat 已经部署过了 ✓ 部署完成。 正在验证部署... ✗ 验证失败。模型可能未正确部署。 ! 请尝试使用以下命令手动启动模型: easy-byzerllm chat deepseek_chat 你好 ✓ 初始化完成。

sunweihunu avatar Nov 27 '24 15:11 sunweihunu

easy-byzerllm chat deepseek_chat 你好

Command Line Arguments:

command : query ray_address : auto model : deepseek_chat query : 你好 template : auto file : None output_file :

✓ Ray is already running 2024-11-27 23:13:52,988 INFO worker.py:1634 -- Connecting to existing Ray cluster at address: 192.168.1.103:6379... 2024-11-27 23:13:52,996 INFO worker.py:1810 -- Connected to Ray cluster. View the dashboard at 127.0.0.1:8265 2024-11-27 23:13:53,665 ERROR serialization.py:462 -- Failed to unpickle serialized exception Traceback (most recent call last): File "/home/dell/.local/lib/python3.10/site-packages/ray/exceptions.py", line 51, in from_ray_exception return pickle.loads(ray_exception.serialized_exception) TypeError: APIStatusError.init() missing 2 required keyword-only arguments: 'response' and 'body'

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "/home/dell/.local/lib/python3.10/site-packages/ray/_private/serialization.py", line 460, in deserialize_objects obj = self._deserialize_object(data, metadata, object_ref) File "/home/dell/.local/lib/python3.10/site-packages/ray/_private/serialization.py", line 342, in _deserialize_object return RayError.from_bytes(obj) File "/home/dell/.local/lib/python3.10/site-packages/ray/exceptions.py", line 45, in from_bytes return RayError.from_ray_exception(ray_exception) File "/home/dell/.local/lib/python3.10/site-packages/ray/exceptions.py", line 54, in from_ray_exception raise RuntimeError(msg) from e RuntimeError: Failed to unpickle serialized exception Traceback (most recent call last): File "/home/dell/.local/bin/easy-byzerllm", line 8, in sys.exit(main()) File "/home/dell/.local/lib/python3.10/site-packages/byzerllm/easy_byzerllm_command.py", line 138, in main byzerllm_main( File "/home/dell/.local/lib/python3.10/site-packages/byzerllm/byzerllm_command.py", line 147, in main resp = llm_client.chat_oai( File "/home/dell/.local/lib/python3.10/site-packages/byzerllm/utils/client/byzerllm_client.py", line 1213, in chat_oai res = self._query(model, v) File "/home/dell/.local/lib/python3.10/site-packages/byzerllm/utils/client/byzerllm_client.py", line 1898, in _query raise inst File "/home/dell/.local/lib/python3.10/site-packages/byzerllm/utils/client/byzerllm_client.py", line 1888, in _query res = ray.get(worker.async_apply.remote(new_input_value)) File "/home/dell/.local/lib/python3.10/site-packages/ray/_private/auto_init_hook.py", line 21, in auto_init_wrapper return fn(*args, **kwargs) File "/home/dell/.local/lib/python3.10/site-packages/ray/_private/client_mode_hook.py", line 103, in wrapper return func(*args, **kwargs) File "/home/dell/.local/lib/python3.10/site-packages/ray/_private/worker.py", line 2753, in get values, debugger_breakpoint = worker.get_objects(object_refs, timeout=timeout) File "/home/dell/.local/lib/python3.10/site-packages/ray/_private/worker.py", line 906, in get_objects raise value ray.exceptions.RaySystemError: System error: Failed to unpickle serialized exception traceback: Traceback (most recent call last): File "/home/dell/.local/lib/python3.10/site-packages/ray/exceptions.py", line 51, in from_ray_exception return pickle.loads(ray_exception.serialized_exception) TypeError: APIStatusError.init() missing 2 required keyword-only arguments: 'response' and 'body'

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "/home/dell/.local/lib/python3.10/site-packages/ray/_private/serialization.py", line 460, in deserialize_objects obj = self._deserialize_object(data, metadata, object_ref) File "/home/dell/.local/lib/python3.10/site-packages/ray/_private/serialization.py", line 342, in _deserialize_object return RayError.from_bytes(obj) File "/home/dell/.local/lib/python3.10/site-packages/ray/exceptions.py", line 45, in from_bytes return RayError.from_ray_exception(ray_exception) File "/home/dell/.local/lib/python3.10/site-packages/ray/exceptions.py", line 54, in from_ray_exception raise RuntimeError(msg) from e RuntimeError: Failed to unpickle serialized exception

sunweihunu avatar Nov 27 '24 15:11 sunweihunu

参看这篇来排查:https://uelng8wukz.feishu.cn/wiki/CcAgwtL9TiuMEOkGoXbcKE3Gnfb?fromScene=spaceOverview

allwefantasy avatar Nov 28 '24 00:11 allwefantasy

也报了同样的错误,查看文档也没有解决,请问有其他方案么?

xiangel avatar Jan 04 '25 10:01 xiangel

也报了同样的错误,查看文档也没有解决,请问有其他方案么?

根据文档,把 ray 中的 err 日志贴出来哦

allwefantasy avatar Jan 07 '25 13:01 allwefantasy

测试了一下使用qwen就不报错,使用deepseek会报错,错误信息和前面的一致

xiangel avatar Jan 14 '25 10:01 xiangel