[Bug] Installation failed due to "Segmentation fault" #3352
Description
🐛 Bug
To Reproduce
I followed MLC-LLM installation guideline here https://llm.mlc.ai/docs/install/mlc_llm.html#install-mlc-packages.
I created a new conda env with python 3.13, and then use pip to install package:
conda activate your-environment
python -m pip install --pre -U -f https://mlc.ai/wheels mlc-llm-nightly-cu128 mlc-ai-nightly-cu128
After installed, I tested via python -m mlc_llm --help but met Segmentation fault:
/home/username/anaconda3/envs/mlc/lib/python3.13/site-packages/torch/cuda/__init__.py:63: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you.
import pynvml # type: ignore[import]
!!!!!!! Segfault encountered !!!!!!!
File "/build/glibc-B3wQXB/glibc-2.31/signal/../sysdeps/unix/sysv/linux/x86_64/sigaction.c", line 0, in 0x00007fd62280908f
Segmentation fault (core dumped)
Environment
- Platform (e.g. WebGPU/Vulkan/IOS/Android/CUDA): CUDA
- Operating system (e.g. Ubuntu/Windows/MacOS/...): Linux
- How you installed MLC-LLM (
conda, source): pip - How you installed TVM (
pip, source): pip - Python version (e.g. 3.10): 3.13
- GPU driver version (if applicable): 575.51.03
- CUDA/cuDNN version (if applicable): 12.9
Can anyone help with this issue? Thanks in advance.