HswOAuth/llm_course
19
16
Fork 0
Code Issues 608 Pull Requests Actions Packages Projects Releases Wiki Activity

本地部署oneapi+fastgpt配置渠道后测试报错 #423

New Issue
Open
opened 2024-12-17 15:46:06 +08:00 by aiscool · 4 comments
aiscool commented 2024-12-17 15:46:06 +08:00
Copy Link

1、xinference已经部署在autodl上并且本地做好了通道;
2、oneapi配置页面没有llama3.1模型供选择，所以我只有自己填了一个qwen2.5-instruct；
3、报错内容确实是我的xinference地址，但是后面加了/v1/chat/completions，不知道是啥？我xinference访问测试模型是正常的。

1、xinference已经部署在autodl上并且本地做好了通道; 2、oneapi配置页面没有llama3.1模型供选择，所以我只有自己填了一个qwen2.5-instruct； 3、报错内容确实是我的xinference地址，但是后面加了/v1/chat/completions，不知道是啥？我xinference访问测试模型是正常的。
2.png
5.1 KiB
1.png
50 KiB
3.png
39 KiB
4.png
30 KiB
5.png
59 KiB
2.png 1.png 3.png 4.png 5.png
x commented 2024-12-17 18:48:18 +08:00
Copy Link
  1. xinference的部署命令和 ‘本地做好了通道’ 做通道的命令截图看一下
  2. 实际部署了什么模型在oneapi自行填写即可，实际部署了llama3.1在下方自行填写就行截屏2024-12-17 18.41.55.png
  3. /v1/chat/completions 是对话模型接口，点击测试时，实际就是向这个接口发送了一个简短的消息，看接口是否可用
1. xinference的部署命令和 ‘本地做好了通道’ 做通道的命令截图看一下 2. 实际部署了什么模型在oneapi自行填写即可，实际部署了llama3.1在下方自行填写就行![截屏2024-12-17 18.41.55.png](/attachments/063e4171-8dae-4c8d-94c2-2faad3a0e9fc) 3. /v1/chat/completions 是对话模型接口，点击测试时，实际就是向这个接口发送了一个简短的消息，看接口是否可用
截屏2024-12-17 18.41.55.png
24 KiB
aiscool commented 2024-12-19 09:47:54 +08:00
Author
Copy Link

xinference的部署命令和 ‘本地做好了通道’ 做通道的命令截图，请老师再看看

xinference的部署命令和 ‘本地做好了通道’ 做通道的命令截图，请老师再看看
image.png
91 KiB
2.png
12 KiB
1.png
59 KiB
image.png 2.png 1.png
aiscool commented 2024-12-19 10:41:05 +08:00
Author
Copy Link

已经把docker所有容器和镜像都删除了，执行docker-compose来重建的，还是报错：2024-12-19 10:35:52 mysql | 2024-12-19T02:35:52.526954Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11
2024-12-19 10:35:53 mysql | 2024-12-19T02:35:53.527210Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11
2024-12-19 10:35:53 mongo | Waiting for MongoDB to start...
2024-12-19 10:35:54 mysql | 2024-12-19T02:35:54.527573Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11
2024-12-19 10:35:55 mysql | 2024-12-19T02:35:55.527963Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11
2024-12-19 10:35:55 mongo | Waiting for MongoDB to start...
2024-12-19 10:35:56 mysql | 2024-12-19T02:35:56.528259Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11
2024-12-19 10:35:57 mysql | 2024-12-19T02:35:57.528471Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11
2024-12-19 10:35:58 mongo | Waiting for MongoDB to start...
2024-12-19 10:35:58 mysql | 2024-12-19T02:35:58.528707Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11
2024-12-19 10:35:59 mysql | 2024-12-19T02:35:59.529052Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11

已经把docker所有容器和镜像都删除了，执行docker-compose来重建的，还是报错：2024-12-19 10:35:52 mysql | 2024-12-19T02:35:52.526954Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11 2024-12-19 10:35:53 mysql | 2024-12-19T02:35:53.527210Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11 2024-12-19 10:35:53 mongo | Waiting for MongoDB to start... 2024-12-19 10:35:54 mysql | 2024-12-19T02:35:54.527573Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11 2024-12-19 10:35:55 mysql | 2024-12-19T02:35:55.527963Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11 2024-12-19 10:35:55 mongo | Waiting for MongoDB to start... 2024-12-19 10:35:56 mysql | 2024-12-19T02:35:56.528259Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11 2024-12-19 10:35:57 mysql | 2024-12-19T02:35:57.528471Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11 2024-12-19 10:35:58 mongo | Waiting for MongoDB to start... 2024-12-19 10:35:58 mysql | 2024-12-19T02:35:58.528707Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11 2024-12-19 10:35:59 mysql | 2024-12-19T02:35:59.529052Z 1 [ERROR] [MY-012574] [InnoDB] Unable to lock ./ibdata1 error: 11
x commented 2024-12-20 12:32:27 +08:00
Copy Link

你在前面的步骤中，成功打开了xinference和onepai，说明这两个已经部署成功。在oneapi中添加xinference模型的步骤如下：

  1. 部署xinference（这个你之前部署成功）
  2. 打通道：ssh -CNgv -L 9997:127.0.0.1:9997 -p 35433 root@connect.westb.seetacloud.com（-p 35433 root@connect.westb.seetacloud.com部分改成自己的机器）
  3. xinference部署模型和验证（这个你之前部署成功）
  4. 本机部署oneapi（这个你之前部署成功）
  5. 将xinference添加到one API， 配置如下：
    截屏2024-12-20 11.48.26.png
你在前面的步骤中，成功打开了xinference和onepai，说明这两个已经部署成功。在oneapi中添加xinference模型的步骤如下： 1. 部署xinference（这个你之前部署成功） 2. 打通道：ssh -CNgv -L 9997:127.0.0.1:9997 -p 35433 root@connect.westb.seetacloud.com（-p 35433 root@connect.westb.seetacloud.com部分改成自己的机器） 3. xinference部署模型和验证（这个你之前部署成功） 4. 本机部署oneapi（这个你之前部署成功） 5. 将xinference添加到one API， 配置如下： ![截屏2024-12-20 11.48.26.png](/attachments/8325b909-28b4-4efd-8b39-3be11523826d)
截屏2024-12-20 11.48.26.png
228 KiB
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels   
bug

Something is not working

  
duplicate

This issue or pull request already exists

  
enhancement

New feature

  
help wanted

Need some help

  
invalid

Something is wrong

  
question

More information is needed

  
wontfix

This won't be fixed

No Label
bug
duplicate
enhancement
help wanted
invalid
question
wontfix
Milestone
Clear milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
No Assignees
2 Participants
Notifications
Due Date
The due date is invalid or out of range. Please use the format 'yyyy-mm-dd'.

No due date set.

Dependencies

No dependencies set.

Reference: HswOAuth/llm_course#423
No description provided.
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?