from pytorch_quantization import cuda_ext filed

[xpww]

Description

After installing pytorch-quantization, the following error occurs when using it:

ImportError: /lib/x86_64-linux-gnu/libc.so.6: version GLIBC_2.32' not found (required by /home/mrpp/software/anaconda3/envs/PyTorch/lib/python3.10/site-packages /pytorch_quantization/cuda_ext.cpython-310-x86_64-linux-gnu.so)`

Environment

TensorRT Version:
8.6.1
NVIDIA GPU:

NVIDIA-SMI 545.23.08 Driver Version: 545.23.08 CUDA Version: 12.3

Operating System:
ubuntu2004

Python Version (if applicable):
3.1.13
Tensorflow Version (if applicable):

PyTorch Version (if applicable):
2.2.0
Baremetal or Container (if so, version):

Relevant Files

import pytorch_quantization
  File "/home/mrpp/software/pycharm/plugins/python/helpers/pydev/_pydev_bundle/pydev_import_hook.py", line 21, in do_import
    module = self._system_import(name, *args, **kwargs)
  File "/home/mrpp/software/anaconda3/envs/PyTorch/lib/python3.10/site-packages/pytorch_quantization/__init__.py", line 20, in <module>
    from .quant_modules import *
  File "/home/mrpp/software/pycharm/plugins/python/helpers/pydev/_pydev_bundle/pydev_import_hook.py", line 21, in do_import
    module = self._system_import(name, *args, **kwargs)
  File "/home/mrpp/software/anaconda3/envs/PyTorch/lib/python3.10/site-packages/pytorch_quantization/quant_modules.py", line 23, in <module>
    from pytorch_quantization import nn as quant_nn
  File "/home/mrpp/software/pycharm/plugins/python/helpers/pydev/_pydev_bundle/pydev_import_hook.py", line 21, in do_import
    module = self._system_import(name, *args, **kwargs)
  File "/home/mrpp/software/anaconda3/envs/PyTorch/lib/python3.10/site-packages/pytorch_quantization/nn/__init__.py", line 19, in <module>
    from pytorch_quantization.nn.modules.tensor_quantizer import *
  File "/home/mrpp/software/pycharm/plugins/python/helpers/pydev/_pydev_bundle/pydev_import_hook.py", line 21, in do_import
    module = self._system_import(name, *args, **kwargs)
  File "/home/mrpp/software/anaconda3/envs/PyTorch/lib/python3.10/site-packages/pytorch_quantization/nn/modules/tensor_quantizer.py", line 24, in <module>
    from pytorch_quantization.tensor_quant import QuantDescriptor, tensor_quant, fake_tensor_quant, scaled_e4m3
  File "/home/mrpp/software/pycharm/plugins/python/helpers/pydev/_pydev_bundle/pydev_import_hook.py", line 21, in do_import
    module = self._system_import(name, *args, **kwargs)
  File "/home/mrpp/software/anaconda3/envs/PyTorch/lib/python3.10/site-packages/pytorch_quantization/tensor_quant.py", line 28, in <module>
    from pytorch_quantization import cuda_ext
  File "/home/mrpp/software/pycharm/plugins/python/helpers/pydev/_pydev_bundle/pydev_import_hook.py", line 21, in do_import
    module = self._system_import(name, *args, **kwargs)
ImportError: /lib/x86_64-linux-gnu/libc.so.6: version `GLIBC_2.32' not found (required by /home/mrpp/software/anaconda3/envs/PyTorch/lib/python3.10/site-packages/pytorch_quantization/cuda_ext.cpython-310-x86_64-linux-gnu.so)

Model link:

Steps To Reproduce

Commands or scripts:

import pytorch_quantization
from pytorch_quantization import cuda_ext

Have you tried the latest release?:
yes

The glibc of ubuntu2004 is version 2.31, which means that the latest pytorch_quantization does not support ubuntu2004?

[xpww]

Resolved, must build from source

[zerollzeng]

closed as it has been solved.

[changg10]

Resolved, must build from source

Which one is the value of building from source code?