OpenBMB / MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone
Apache License 2.0
7.98k stars 558 forks source link

[Request] - Support for mobile NPU deployment #180

Closed LongIslandWithoutIceTea closed 1 month ago

LongIslandWithoutIceTea commented 1 month ago

Hi guys,

Just wondering if you guys have plans to support quantization and deployment on mobile NPUs like those on the Qualcomm Snapdragon in the future?

Thanks for your time!

iceflame89 commented 1 month ago

Speeding up with NPU has been in our plan from the beginning. It's almost done, please stay tuned.