Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

xinrerence 0.14版本 llama_cpp_python 依赖安装的报错 #2006

Closed
1 of 3 tasks
Gogoworks opened this issue Aug 3, 2024 · 3 comments
Closed
1 of 3 tasks

xinrerence 0.14版本 llama_cpp_python 依赖安装的报错 #2006

Gogoworks opened this issue Aug 3, 2024 · 3 comments
Labels
Milestone

Comments

@Gogoworks
Copy link

System Info / 系統信息

Ubuntu 20.24 LTS
CDUD 12.4
vllm 0.5.3.post1
vllm-flash-attn 2.5.9.post1
sentence-transformers 3.0.1
transformers 4.43.3
transformers-stream-generator 0.0.5
llama-cpp-python 0.2.82

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece?

  • docker / docker
  • pip install / 通过 pip install 安装
  • installation from source / 从源码安装

Version info / 版本信息

xinrerence 0.14版本

The command used to start Xinference / 用以启动 xinference 的命令

XINFERENCE_HOME=/data/models/xinference/models XINFERENCE_MODEL_SRC=modelscope HF_ENDPOINT=https://hf-mirror.com CUDA_VISIBLE_DEVICES=0 xinference-local --host 0.0.0.0 --port 9997 --auth-config /data/models/xinference/auth_config.json --log-level debug

Reproduction / 复现过程

安装:llama_cpp_python-0.2.82
来源 https://abetlen.github.io/llama-cpp-python/whl/cu124/llama-cpp-python/

CMAKE_ARGS="-DLLAMA_CUDA=on" pip install llama_cpp_python-0.2.82-cp310-cp310-linux_x86_64.whl

xinference 启动:

XINFERENCE_HOME=/data/models/xinference/models XINFERENCE_MODEL_SRC=modelscope HF_ENDPOINT=https://hf-mirror.com CUDA_VISIBLE_DEVICES=0 xinference-local --host 0.0.0.0 --port 9997 --auth-config /data/models/xinference/auth_config.json --log-level debug

xinference 后报错

Traceback (most recent call last):
File "/data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/llama_cpp/llama_cpp.py", line 75, in _load_shared_library
return ctypes.CDLL(str(_lib_path), **cdll_args) # type: ignore
File "/data/program/miniconda3/envs/xinference/lib/python3.10/ctypes/init.py", line 374, in init
self._handle = _dlopen(self._name, mode)
OSError: /lib/x86_64-linux-gnu/libc.so.6: version `GLIBC_2.32' not found (required by /data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/llama_cpp/lib/libllama.so)

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/data/program/miniconda3/envs/xinference/bin/xinference-local", line 5, in
from xinference.deploy.cmdline import local
File "/data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/xinference/init.py", line 37, in
_install()
File "/data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/xinference/init.py", line 34, in _install
install_model()
File "/data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/xinference/model/init.py", line 17, in _install
from .llm import _install as llm_install
File "/data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/xinference/model/llm/init.py", line 20, in
from .core import (
File "/data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/xinference/model/llm/core.py", line 26, in
from ...types import PeftModelConfig
File "/data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/xinference/types.py", line 399, in
from llama_cpp import Llama
File "/data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/llama_cpp/init.py", line 1, in
from .llama_cpp import *
File "/data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/llama_cpp/llama_cpp.py", line 88, in
_lib = _load_shared_library(_lib_base_name)
File "/data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/llama_cpp/llama_cpp.py", line 77, in _load_shared_library
raise RuntimeError(f"Failed to load shared library '{_lib_path}': {e}")
RuntimeError: Failed to load shared library '/data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/llama_cpp/lib/libllama.so': /lib/x86_64-linux-gnu/libc.so.6: version `GLIBC_2.32' not found (required by /data/program/miniconda3/envs/xinference/lib/python3.10/site-packages/llama_cpp/lib/libllama.so)
(xinference) root@10-60-176-5:/data/models/xinference/tmp#

Snipaste_2024-08-03_13-20-11

Expected behavior / 期待表现

卸载 llama_cpp_python 启动正常,但是llama cpp 无法加载GPU ;

3f8452bb8611bce0544116ac2a937fd

期待问题解决!

@XprobeBot XprobeBot added the gpu label Aug 3, 2024
@XprobeBot XprobeBot added this to the v0.14.0 milestone Aug 3, 2024
@Gogoworks
Copy link
Author

更换ubuntu 22.04 LTS 解决问题

@oom2018
Copy link

oom2018 commented Aug 17, 2024

更换ubuntu 22.04 LTS 解决问题

如何更换呢?

@Mercury-ming
Copy link

同问,centos7.9 也是这问题,RuntimeError: Failed to load shared library '/root/anaconda3/envs/xinference/lib/python3.11/site-packages/llama_cpp/lib/libllama.so': /lib64/libc.so.6: version `GLIBC_2.32' not found (required by /root/anaconda3/envs/xinference/lib/python3.11/site-packages/llama_cpp/lib/libllama.so)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

4 participants