Skip to content

/lib64/libc.so.6: version `GLIBC_2.14' not found #6021

@guotong1988

Description

@guotong1988

Describe the bug

Linux-CPU inference

Java code

System information

  • OS Platform and Distribution (e.g., Linux Ubuntu 16.04):

CentOS

  • ONNX Runtime installed from (source or binary):

I don't know whether onnx is installed in the Linux machine.

I can not run yum install libgomp in the machine.

I put libgomp.so.1 into the jar-file and use System.setProperty("java.library.path", ... )

  • ONNX Runtime version:
    in pom.xml (I think it is the way onnx installed)
  <dependency>
            <groupId>com.microsoft.onnxruntime</groupId>
            <artifactId>onnxruntime</artifactId>
            <version>1.5.2</version>
  </dependency>
  • Python version: 3.6

  • GCC/Compiler version (if compiling from source): dont know

Additional context
I can run the onnx model inference in my Macbook in java.
I use python to export the onnx-model-file and try to load it by java.

libgomp version: libgomp-4.8.5-44.el7.x86_64

The exact error:
java.lang.UnsatisfiedLinkError: /path/to/onnxruntime-java7108564327804271519/libonnxruntime.so: /lib64/libc.so.6: version 'GLIBC_2.14' not found (required by /path/to/onnxruntime-java7108564327804271519/libonnxruntime.so)

at java.lang.ClassLoader$NativeLibrary.load(Native Method)
	at java.lang.ClassLoader.loadLibrary0(ClassLoader.java:1941)
	at java.lang.ClassLoader.loadLibrary(ClassLoader.java:1824)
	at java.lang.Runtime.load0(Runtime.java:809)
	at java.lang.System.load(System.java:1086)
	at ai.onnxruntime.OnnxRuntime.load(OnnxRuntime.java:199)
	at ai.onnxruntime.OnnxRuntime.init(OnnxRuntime.java:87)
	at ai.onnxruntime.OrtEnvironment.<clinit>(OrtEnvironment.java:24)
	at com.mycode.onnx_test.ScoreMNIST.main(ScoreMNIST.java:288)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions