inference icon indicating copy to clipboard operation
inference copied to clipboard

QUESTION: Could not build wheels for llama-cpp-python, which is required to install pyproject.toml-based projects

Open shanton23 opened this issue 1 year ago • 17 comments

Describe the bug

ERROR: Failed building wheel for llama-cpp-python Failed to build llama-cpp-python ERROR: Could not build wheels for llama-cpp-python, which is required to install pyproject.toml-based projects

To Reproduce

My os is Ubuntu20.04lts, and i use miniconda to create a totally new environment. When running 'pip install 'xinference[all]', I got this error.

shanton23 avatar Oct 25 '23 08:10 shanton23

Do you have GPU cards on your machine?

aresnow1 avatar Oct 26 '23 03:10 aresnow1

Hello, this issue is typically caused by incompatible GCC versions. Could you please provide the full installation log?

UranusSeven avatar Oct 26 '23 06:10 UranusSeven

@shanton23 Hi, were you able to solve this problem? Is there anything I can help?

UranusSeven avatar Oct 27 '23 08:10 UranusSeven

Do you have GPU cards on your machine?

I hava a 4090.

shanton23 avatar Nov 02 '23 02:11 shanton23

@shanton23 Hi, were you able to solve this problem? Is there anything I can help?

Hello, this issue is typically caused by incompatible GCC versions. Could you please provide the full installation log?

My gcc version is 9.4.0 (Ubuntu 9.4.0-1ubuntu1~20.04.1).

shanton23 avatar Nov 02 '23 02:11 shanton23

I also have the same problem, how can I solve it? It appeared when I installed llama-spp-python.

bizheyandebing avatar Dec 19 '23 13:12 bizheyandebing

After I upgraded gcc through the following command “sudo apt install gcc-11 g++-11”, this problem has not been improved. I hope to get your help. Thank you very much.

bizheyandebing avatar Dec 19 '23 13:12 bizheyandebing

Perhaps, can you directly share a requirements.txt or environment.yaml used to create a conda environment?

bizheyandebing avatar Dec 19 '23 13:12 bizheyandebing

You can follow this "https://zhuanlan.zhihu.com/p/592894910?utm_id=0" up the gcc version to 11.2.1 20220127 (Red Hat 11.2.1-9) (GCC) (i am centos7)

kukuze avatar Jan 15 '24 14:01 kukuze

升级到11了,还是不行 image

QiuZiXian avatar Jun 18 '24 10:06 QiuZiXian

我也有同样的问题,gcc 13,python 3.11,cuda 12.1

bclovetkd avatar Jul 09 '24 02:07 bclovetkd

我也有同样的问题,gcc 13,python 3.11,cuda 12.1

0.2.82太新了,编译不了,手动装一下老一点的版本 pip install llama-cpp-python==0.2.80

ques666 avatar Jul 09 '24 17:07 ques666

我也有同样的问题,gcc 13,python 3.11,cuda 12.1

0.2.82太新了,编译不了,手动装一下老一点的版本 pip install llama-cpp-python==0.2.80

大哥chatglm-cpp多少版本的合适呢

ASan1527 avatar Jul 11 '24 02:07 ASan1527

我也有同样的问题,gcc 13,python 3.11,cuda 12.1

0.2.82太新了,编译不了,手动装一下老一点的版本 pip install llama-cpp-python==0.2.80

大哥chatglm-cpp多少版本的合适呢

我用 0.4.0没问题,你的chatglm-cpp应该不是版本问题,可以新建一个conda环境试一下

ques666 avatar Jul 11 '24 06:07 ques666

llama-cpp-python==0.2.80

为啥我用0.2.80还是不行呢

thinkinds avatar Jul 22 '24 02:07 thinkinds

llama-cpp-python==0.2.80

为啥我用0.2.80还是不行呢

新建的conda环境吗?

ques666 avatar Jul 22 '24 06:07 ques666

This issue is stale because it has been open for 7 days with no activity.

github-actions[bot] avatar Aug 08 '24 19:08 github-actions[bot]

This issue was closed because it has been inactive for 5 days since being marked as stale.

github-actions[bot] avatar Aug 13 '24 19:08 github-actions[bot]