Servering C++ 编译失败

[shengzhou1216]

环境

docker images: paddlepaddle/paddle:latest-dev-cuda11.4.1-cudnn8-gcc82

复现

按照 如何编译PaddleServing文档，在 编译paddle-serving-server步骤中 make -j20 这一步出错.

编译时，设置了代理，可以从Github上拉取资源

错误信息

CMake Error at extern_paddle-stamp/download-extern_paddle.cmake:159 (message):
  Each download failed!

    error: downloading 'http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz' failed
         status_code: 22
         status_string: "HTTP response code said error"
         log:
         --- LOG BEGIN ---
         Uses proxy env variable http_proxy == 'http://10.171.60.50:7890'
    Trying 10.171.60.50:7890...

  TCP_NODELAY set

  Connected to 10.171.60.50 (10.171.60.50) port 7890 (#0)

  GET
  http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz
  HTTP/1.1

  Host: paddle-inference-lib.bj.bcebos.com

  User-Agent: curl/7.65.0

  Accept: */*

  Proxy-Connection: Keep-Alive

  

  Mark bundle as not supporting multiuse

  The requested URL returned error: 404 Not Found

  Closing connection 0

  

         --- LOG END ---
         error: downloading 'http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz' failed
         status_code: 22
         status_string: "HTTP response code said error"
         log:
         --- LOG BEGIN ---
         Uses proxy env variable http_proxy == 'http://10.171.60.50:7890'
    Trying 10.171.60.50:7890...

  TCP_NODELAY set

  Connected to 10.171.60.50 (10.171.60.50) port 7890 (#0)

  GET
  http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz
  HTTP/1.1

  Host: paddle-inference-lib.bj.bcebos.com

  User-Agent: curl/7.65.0

  Accept: */*

  Proxy-Connection: Keep-Alive

  

  Mark bundle as not supporting multiuse

  The requested URL returned error: 404 Not Found

  Closing connection 0

  

         --- LOG END ---
         error: downloading 'http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz' failed
         status_code: 22
         status_string: "HTTP response code said error"
         log:
         --- LOG BEGIN ---
         Uses proxy env variable http_proxy == 'http://10.171.60.50:7890'
    Trying 10.171.60.50:7890...

  TCP_NODELAY set

  Connected to 10.171.60.50 (10.171.60.50) port 7890 (#0)

  GET
  http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz
  HTTP/1.1

  Host: paddle-inference-lib.bj.bcebos.com

  User-Agent: curl/7.65.0

  Accept: */*

  Proxy-Connection: Keep-Alive

  

  Mark bundle as not supporting multiuse

  The requested URL returned error: 404 Not Found

  Closing connection 0

  

         --- LOG END ---
         error: downloading 'http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz' failed
         status_code: 22
         status_string: "HTTP response code said error"
         log:
         --- LOG BEGIN ---
         Uses proxy env variable http_proxy == 'http://10.171.60.50:7890'
    Trying 10.171.60.50:7890...

  TCP_NODELAY set

  Connected to 10.171.60.50 (10.171.60.50) port 7890 (#0)

  GET
  http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz
  HTTP/1.1

  Host: paddle-inference-lib.bj.bcebos.com

  User-Agent: curl/7.65.0

  Accept: */*

  Proxy-Connection: Keep-Alive

  

  Mark bundle as not supporting multiuse

  The requested URL returned error: 404 Not Found

  Closing connection 0

  

         --- LOG END ---
         error: downloading 'http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz' failed
         status_code: 22
         status_string: "HTTP response code said error"
         log:
         --- LOG BEGIN ---
         Uses proxy env variable http_proxy == 'http://10.171.60.50:7890'
    Trying 10.171.60.50:7890...

  TCP_NODELAY set

  Connected to 10.171.60.50 (10.171.60.50) port 7890 (#0)

  GET
  http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz
  HTTP/1.1

  Host: paddle-inference-lib.bj.bcebos.com

  User-Agent: curl/7.65.0

  Accept: */*

  Proxy-Connection: Keep-Alive

  

  Mark bundle as not supporting multiuse

  The requested URL returned error: 404 Not Found

  Closing connection 0

  

         --- LOG END ---
         error: downloading 'http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz' failed
         status_code: 22
         status_string: "HTTP response code said error"
         log:
         --- LOG BEGIN ---
         Uses proxy env variable http_proxy == 'http://10.171.60.50:7890'
    Trying 10.171.60.50:7890...

  TCP_NODELAY set

  Connected to 10.171.60.50 (10.171.60.50) port 7890 (#0)

  GET
  http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU//paddle_inference.tgz
  HTTP/1.1

  Host: paddle-inference-lib.bj.bcebos.com

  User-Agent: curl/7.65.0

  Accept: */*

  Proxy-Connection: Keep-Alive

  

  Mark bundle as not supporting multiuse

  The requested URL returned error: 404 Not Found

  Closing connection 0

  

         --- LOG END ---
         
    


CMakeFiles/extern_paddle.dir/build.make:90: recipe for target 'third_party/Paddle/src/extern_paddle-stamp/extern_paddle-download' failed
make[2]: *** [third_party/Paddle/src/extern_paddle-stamp/extern_paddle-download] Error 1
CMakeFiles/Makefile2:487: recipe for target 'CMakeFiles/extern_paddle.dir/all' failed
make[1]: *** [CMakeFiles/extern_paddle.dir/all] Error 2
Makefile:129: recipe for target 'all' failed
make: *** [all] Error 2

[shengzhou1216]

日志中显示404错误，请问资源是否确定存在？

[pupubushilulu]

我遇到了同样的问题，请问解决了吗

[diana-pwf]

I met the same question too. It seems that the file http://paddle-inference-lib.bj.bcebos.com/2.3.0-rc0/cxx_c/Linux/GPU/x86-64_gcc8.2_avx_mkl_cuda10.2_cudnn7.6.5_trt6.0.1.5/paddle_inference.tgz doesn't exist. Hoping to get help.

[v587xpt]

这个问题有大佬解决了吗？我也遇到这个问题了，好烦啊啊啊啊啊啊；能给出个解决办法吗