Android app support?
#1
by
jadbox
- opened
Does anyone know what Android apps exist to use QLORA models like this one? Also does llama.cpp support it?
Does anyone know what Android apps exist to use QLORA models like this one? Also does llama.cpp support it?
Yes ExecuTorch supports the export and inference e2e flow. Please find documentation here along with sample Android apps - https://github.com/pytorch/executorch/blob/main/examples/demo-apps/android/LlamaDemo/docs/delegates/xnnpack_README.md