Comments (21)
qinxuye
commented on September 22, 2024
2
那看来和端口无关，有可能是windows 不能指定 0.0.0.0，换成你的 IP 试下
from inference.
qinxuye
commented on September 22, 2024
看看 9997 是不是被占用了。
from inference.
cq134cq
commented on September 22, 2024
看看 9997 是不是被占用了。
看过没有被占用，还有
from inference.
cq134cq
commented on September 22, 2024
看看 9997 是不是被占用了。
(c:\soft\xx) C:\soft\xx>netstat -na
活动连接
协议 本地地址 外部地址 状态
TCP 0.0.0.0:135 0.0.0.0:0 LISTENING
TCP 0.0.0.0:445 0.0.0.0:0 LISTENING
TCP 0.0.0.0:5040 0.0.0.0:0 LISTENING
TCP 0.0.0.0:6686 0.0.0.0:0 LISTENING
TCP 0.0.0.0:6687 0.0.0.0:0 LISTENING
TCP 0.0.0.0:6688 0.0.0.0:0 LISTENING
TCP 0.0.0.0:6689 0.0.0.0:0 LISTENING
TCP 0.0.0.0:6711 0.0.0.0:0 LISTENING
TCP 0.0.0.0:7680 0.0.0.0:0 LISTENING
TCP 0.0.0.0:13688 0.0.0.0:0 LISTENING
TCP 0.0.0.0:49664 0.0.0.0:0 LISTENING
TCP 0.0.0.0:49665 0.0.0.0:0 LISTENING
TCP 0.0.0.0:49666 0.0.0.0:0 LISTENING
TCP 0.0.0.0:49667 0.0.0.0:0 LISTENING
TCP 0.0.0.0:49669 0.0.0.0:0 LISTENING
TCP 0.0.0.0:49710 0.0.0.0:0 LISTENING
TCP 0.0.0.0:49732 0.0.0.0:0 LISTENING
TCP 10.0.100.191:139 0.0.0.0:0 LISTENING
TCP 10.0.100.191:49408 20.197.71.89:443 ESTABLISHED
TCP 10.0.100.191:49680 123.56.99.17:3570 ESTABLISHED
TCP 10.0.100.191:49709 42.192.32.66:443 ESTABLISHED
TCP 10.0.100.191:49876 58.217.207.240:443 ESTABLISHED
TCP 10.0.100.191:49881 58.217.207.240:8081 ESTABLISHED
TCP 10.0.100.191:49882 0.0.0.0:0 LISTENING
TCP 10.0.100.191:49883 10.0.100.171:20000 ESTABLISHED
TCP 10.0.100.191:49980 23.22.146.5:443 TIME_WAIT
TCP 10.0.100.191:49995 44.224.154.229:443 TIME_WAIT
TCP 127.0.0.1:5533 0.0.0.0:0 LISTENING
TCP 127.0.0.1:5533 127.0.0.1:49673 ESTABLISHED
TCP 127.0.0.1:5533 127.0.0.1:49676 ESTABLISHED
TCP 127.0.0.1:5533 127.0.0.1:49681 ESTABLISHED
TCP 127.0.0.1:5533 127.0.0.1:49682 ESTABLISHED
TCP 127.0.0.1:5533 127.0.0.1:49688 ESTABLISHED
TCP 127.0.0.1:5533 127.0.0.1:49689 ESTABLISHED
TCP 127.0.0.1:5533 127.0.0.1:49690 ESTABLISHED
TCP 127.0.0.1:5533 127.0.0.1:49692 ESTABLISHED
TCP 127.0.0.1:6688 127.0.0.1:49678 ESTABLISHED
TCP 127.0.0.1:6688 127.0.0.1:49717 ESTABLISHED
TCP 127.0.0.1:6688 127.0.0.1:49747 ESTABLISHED
TCP 127.0.0.1:6688 127.0.0.1:49819 ESTABLISHED
TCP 127.0.0.1:6689 127.0.0.1:49772 ESTABLISHED
TCP 127.0.0.1:6690 0.0.0.0:0 LISTENING
TCP 127.0.0.1:6711 127.0.0.1:49894 ESTABLISHED
TCP 127.0.0.1:35600 0.0.0.0:0 LISTENING
TCP 127.0.0.1:35600 127.0.0.1:49789 ESTABLISHED
TCP 127.0.0.1:35600 127.0.0.1:49880 ESTABLISHED
TCP 127.0.0.1:35800 0.0.0.0:0 LISTENING
TCP 127.0.0.1:49635 0.0.0.0:0 LISTENING
TCP 127.0.0.1:49673 127.0.0.1:5533 ESTABLISHED
TCP 127.0.0.1:49676 127.0.0.1:5533 ESTABLISHED
TCP 127.0.0.1:49678 127.0.0.1:6688 ESTABLISHED
TCP 127.0.0.1:49681 127.0.0.1:5533 ESTABLISHED
TCP 127.0.0.1:49682 127.0.0.1:5533 ESTABLISHED
TCP 127.0.0.1:49688 127.0.0.1:5533 ESTABLISHED
TCP 127.0.0.1:49689 127.0.0.1:5533 ESTABLISHED
TCP 127.0.0.1:49690 127.0.0.1:5533 ESTABLISHED
TCP 127.0.0.1:49692 127.0.0.1:5533 ESTABLISHED
TCP 127.0.0.1:49717 127.0.0.1:6688 ESTABLISHED
TCP 127.0.0.1:49740 127.0.0.1:49741 ESTABLISHED
TCP 127.0.0.1:49741 127.0.0.1:49740 ESTABLISHED
TCP 127.0.0.1:49747 127.0.0.1:6688 ESTABLISHED
TCP 127.0.0.1:49750 127.0.0.1:49751 ESTABLISHED
TCP 127.0.0.1:49751 127.0.0.1:49750 ESTABLISHED
TCP 127.0.0.1:49772 127.0.0.1:6689 ESTABLISHED
TCP 127.0.0.1:49775 0.0.0.0:0 LISTENING
TCP 127.0.0.1:49775 127.0.0.1:50004 ESTABLISHED
TCP 127.0.0.1:49776 0.0.0.0:0 LISTENING
TCP 127.0.0.1:49776 127.0.0.1:49843 ESTABLISHED
TCP 127.0.0.1:49789 127.0.0.1:35600 ESTABLISHED
TCP 127.0.0.1:49790 0.0.0.0:0 LISTENING
TCP 127.0.0.1:49791 0.0.0.0:0 LISTENING
TCP 127.0.0.1:49791 127.0.0.1:49795 ESTABLISHED
TCP 127.0.0.1:49795 127.0.0.1:49791 ESTABLISHED
TCP 127.0.0.1:49819 127.0.0.1:6688 ESTABLISHED
TCP 127.0.0.1:49820 0.0.0.0:0 LISTENING
TCP 127.0.0.1:49843 127.0.0.1:49776 ESTABLISHED
TCP 127.0.0.1:49880 127.0.0.1:35600 ESTABLISHED
TCP 127.0.0.1:49894 127.0.0.1:6711 ESTABLISHED
TCP 127.0.0.1:49975 127.0.0.1:49775 TIME_WAIT
TCP 127.0.0.1:49977 127.0.0.1:49775 TIME_WAIT
TCP 127.0.0.1:49996 127.0.0.1:49997 TIME_WAIT
TCP 127.0.0.1:49998 127.0.0.1:49775 TIME_WAIT
TCP 127.0.0.1:50003 127.0.0.1:49775 TIME_WAIT
TCP 127.0.0.1:50004 127.0.0.1:49775 ESTABLISHED
TCP 127.0.0.1:53563 0.0.0.0:0 LISTENING
TCP [::]:135 [::]:0 LISTENING
TCP [::]:445 [::]:0 LISTENING
TCP [::]:7680 [::]:0 LISTENING
TCP [::]:13688 [::]:0 LISTENING
TCP [::]:49664 [::]:0 LISTENING
TCP [::]:49665 [::]:0 LISTENING
TCP [::]:49666 [::]:0 LISTENING
TCP [::]:49667 [::]:0 LISTENING
TCP [::]:49669 [::]:0 LISTENING
TCP [::]:49710 [::]:0 LISTENING
TCP [::]:49732 [::]:0 LISTENING
TCP [::1]:13688 [::1]:49868 ESTABLISHED
TCP [::1]:13688 [::1]:49884 ESTABLISHED
TCP [::1]:13688 [::1]:49885 ESTABLISHED
TCP [::1]:49672 [::]:0 LISTENING
TCP [::1]:49868 [::1]:13688 ESTABLISHED
TCP [::1]:49884 [::1]:13688 ESTABLISHED
TCP [::1]:49885 [::1]:13688 ESTABLISHED
from inference.
qinxuye
commented on September 22, 2024
换个端口能启动吗？
from inference.
cq134cq
commented on September 22, 2024
端口能启动吗
一样报错
(c:\soft\xx) C:\soft\xx>xinference-local --host 0.0.0.0 --port 9996
2024-02-29 10:41:09,087 xinference.core.supervisor 18184 INFO Xinference supervisor 0.0.0.0:38877 started
2024-02-29 10:41:09,116 xinference.core.worker 18184 INFO Starting metrics export server at 0.0.0.0:None
2024-02-29 10:41:09,118 xinference.core.worker 18184 INFO Checking metrics export server...
2024-02-29 10:41:13,880 xinference.core.worker 18184 INFO Metrics server is started at: http://0.0.0.0:50046
2024-02-29 10:41:13,882 xinference.core.worker 18184 INFO Xinference worker 0.0.0.0:38877 started
2024-02-29 10:41:13,884 xinference.core.worker 18184 INFO Purge cache directory: C:\Users\sync.xinference\cache
Traceback (most recent call last):
File "c:\soft\xx\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "c:\soft\xx\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "c:\soft\xx\Scripts\xinference-local.exe_main.py", line 7, in
sys.exit(local())
File "c:\soft\xx\lib\site-packages\click\core.py", line 1157, in call
return self.main(*args, **kwargs)
File "c:\soft\xx\lib\site-packages\click\core.py", line 1078, in main
rv = self.invoke(ctx)
File "c:\soft\xx\lib\site-packages\click\core.py", line 1434, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "c:\soft\xx\lib\site-packages\click\core.py", line 783, in invoke
return __callback(*args, **kwargs)
File "c:\soft\xx\lib\site-packages\xinference\deploy\cmdline.py", line 220, in local
start_local_cluster(
File "c:\soft\xx\lib\site-packages\xinference\deploy\cmdline.py", line 107, in start_local_cluster
main(
File "c:\soft\xx\lib\site-packages\xinference\deploy\local.py", line 122, in main
raise RuntimeError("Cluster is not available after multiple attempts")
RuntimeError: Cluster is not available after multiple attempts
from inference.
cq134cq
commented on September 22, 2024
那看来和端口无关，有可能是windows 不能指定 0.0.0.0，换成你的 IP 试下
换IP就可以了，谢谢
from inference.
qinxuye
commented on September 22, 2024
OK，后续改进下，windows 指定 0.0.0.0 看看如何处理
from inference.
cq134cq
commented on September 22, 2024
用xinference-local --host 0.0.0.0 --port 9997就报错
请问这里如何指定它用GPU
from inference.
qinxuye
commented on September 22, 2024
用xinference-local --host 0.0.0.0 --port 9997就报错
请问这里如何指定它用GPU
有可用的应该会自动选择 GPU 的。
from inference.
cq134cq
commented on September 22, 2024
择 GPU 的
我的机器上有一个4060显卡是空的
from inference.
qinxuye
commented on September 22, 2024
执行 python -c "import torch; print(torch.cuda.is_available())"
看下是否可用。
from inference.
cq134cq
commented on September 22, 2024
执行 python -c "import torch; print(torch.cuda.is_available())"
看下是否可用。
不能用，那是因为什么？
from inference.
qinxuye
commented on September 22, 2024
那看下驱动和 torch 版本对应啊之类的，这个是 pytorch 的安装问题了，不在 xinference 范畴内。
from inference.
cq134cq
commented on September 22, 2024
在 xinference 范畴内
说的没错，是torch 版本问题
from inference.
cq134cq
commented on September 22, 2024
那看下驱动和 torch 版本对应啊之类的，这个是 pytorch 的安装问题了，不在 xinference 范畴内。
在次感谢
from inference.
FinTechCao
commented on September 22, 2024
那看来和端口无关，有可能是windows 不能指定 0.0.0.0，换成你的 IP 试下
请问一下 你的IP 是指什么？比如我要从某地址A去访问部在B地址的xinference，那 -H 后面的参数是地址A吗？
from inference.
zhongzhubailong
commented on September 22, 2024
那看来和端口无关，有可能是windows 不能指定 0.0.0.0，换成你的 IP 试下
请问一下 你的IP 是指什么？比如我要从某地址A去访问部在B地址的xinference，那 -H 后面的参数是地址A吗？
不要指定IP，直接xinference-local启动
from inference.
WHG555
commented on September 22, 2024
使用0.0.0.0 是为了能让本地的所有IP都能连上。 不然还得手动改IP了
from inference.
github-actions
commented on September 22, 2024
This issue is stale because it has been open for 7 days with no activity.
from inference.
github-actions
commented on September 22, 2024
This issue was closed because it has been inactive for 5 days since being marked as stale.
from inference.
Related Issues (20)
- 在Transformers下以8-bit无法启动qwen2模型 HOT 3
- 未设置密码，访问会显示登录界面 HOT 2
- 【BUG】embedding和rerank模型不去掉last config，launch没响应。
- 视频模型不显示 HOT 7
- RuntimeError: Failed to launch model, detail: No such file or directory HOT 1
- Dash-infer support maybe? HOT 1
- benchmark异步并行测试报错 HOT 4
- Xinference 推理时间性能与CPU推理相差不大 HOT 2
- 官方容器启动sglang时报错flashinfer版本太低
- benchmark当并发数超过一定值，系统会报错，有2种报错状态
- 增加多case request请求前缀kv-cache加速机制 HOT 2
- 向语音模型发送请求 HOT 1
- 仍然可复现 HOT 1
- How do I use PyTorch to register a model, and then find that there is no quantization option when I start it up?
- 注册自定义的微调后的Embedding模型时报错 HOT 1
- sglang 启动报错
- internvl2推理异常 HOT 2
- xinference经常丢失模型 HOT 3
- 运行所有的reranker模型，均提示got an unexpected keyword argument 'trust_remote_code' HOT 4
- 下一个模型重复下载多次 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from inference.