m1 MacBook Pro 跑不起来 WebDemo - Githubissues

OpenBMB / MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

Apache License 2.0

7.97k stars 558 forks source link

m1 MacBook Pro 跑不起来 WebDemo #205

Closed ChenzhengUESTC closed 1 month ago

ChenzhengUESTC commented 1 month ago

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

[X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

[X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

按照readme运行demo

期望行为 | Expected Behavior

正常运行

复现方法 | Steps To Reproduce

PYTORCH_ENABLE_MPS_FALLBACK=1 python web_demo.py --device mps

运行环境 | Environment

- OS: osx
- Python: 3.11
- Transformers: 4.40.0
- PyTorch: 2.1.2
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`): None

备注 | Anything else?

iTerm2 六月 03 2024 21:29:40

iceflame89 commented 1 month ago

For MiniCPM-V 2.0: readme

PYTORCH_ENABLE_MPS_FALLBACK=1 python web_demo.py --device mps --dtype fp16

For MiniCPM-Llama3-V 2.5: readme

PYTORCH_ENABLE_MPS_FALLBACK=1 python web_demo_2.5.py --device mps