[Bug] mlc_llm package failed once, and i cant run it again

[CallMeTkt]

🐛 Bug

To Reproduce

Steps to reproduce the behavior:

1. i ran it once, it failed after a few minutes, and now i cant run the command again using a different conda environment or anything

Expected behavior

it to just run again

the code to finish properly

Environment

• Platform (e.g. WebGPU/Vulkan/IOS/Android/CUDA):

• Operating system (e.g. Ubuntu/Windows/MacOS/...): windows

• Device (e.g. iPhone 12 Pro, PC+RTX 3090, ...)

• How you installed MLC-LLM (conda, source): git clone https://github.com/mlc-ai/mlc-llm.git and nightly one khen mentioned

• How you installed TVM-Unity (pip, source): yea

• Python version (e.g. 3.10): 3.11 i think

• GPU driver version (if applicable):

• CUDA/cuDNN version (if applicable):

• TVM Unity Hash Tag (python -c "import tvm; print('\n'.join(f'{k}: {v}' for k, v in tvm.support.libinfo().items()))", applicable if you compile models):

• Any other relevant information:

Additional context

[CallMeTkt]

this is using the new page at https://llm.mlc.ai/docs/deploy/android.html#demo-app that you just added

[AkulRT]

Hey, I think I might be getting the same issue. For me, it is saying mlc_llm: command not found.