hongming yang
hongming yang
nice ```python import os os.environ["MKL_SERVICE_FORCE_INTEL"] = '1' os.environ["MKL_THREADING_LAYER"] = '1' ``` 加重新安装以后成功运行quick start了
> I change squid acl ( file location: /dify/docker/ssrf_proxy/squid.conf.template )like this： > > ``` > > http_access allow Safe_ports > http_access allow CONNECT SSL_ports > http_access allow localhost manager >...
> > I change squid acl ( file location: /dify/docker/ssrf_proxy/squid.conf.template )like this： > > ``` > > > > http_access allow Safe_ports > > http_access allow CONNECT SSL_ports > >...
🔍 **Additional Observation** Interestingly, I encountered the same issue when using `vLLM v0.8.5` to serve the Qwen3-235B FP8 model. After a certain number of requests, the service also becomes unreachable...
> do you have backend logs? has the backend received the requests? Backend server has not received the request
https://zhuanlan.zhihu.com/p/1903867484429353303 我这么部署成功了，你可以试试
可以试试 -e TP_SOCKET_IFNAME=enp199s0f0