[BUG] <title>whether it is possible to deploy minicpmv2.5 on Android based on llama.cpp (using Qualcomm GPU for inference)?

[My-captain]

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

No response

期望行为 | Expected Behavior

May I ask whether it is possible to deploy minicpmv2.5 on Android based on llama.cpp (using Qualcomm GPU for inference)?

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):

备注 | Anything else?

No response

[theoctopusride]

I would like to know about the Qualcomm NPU for inference. +1

[tc-mb]

First of all, I'm sorry that I was busy with other projects before and I responded a little late. Due to the manpower of our team, we cannot support Qualcomm NPU yet.

[My-captain]

Got it, thanks for your response.