qtyandhasee

detailed information :/data/local/tmp/llama-vulkan-test # ls bin :/data/local/tmp/llama-vulkan-test # chmod +x ./* tmp/stories260K.gguf --color -c 2048 -ngl 2 --temp 0.7 -n 128 -p "One day, Lily met" < Log start main:...

> Did you try to build the llama.android example app? @smilingOrange Not really, because I'm not using termux and Android studio, I cross-compile llama.cpp using the NDK and then transfer...

> CMakeLists.txt 中加入这一条就行了 。add_compile_options(-flax-vector-conversions) 请问这条是加在哪里呀？我尝试加入了这个，但是并没有起作用，是不是需要加入到全局变量里？

@anthonyliot Hello! I am also trying to use Android OpenCL recently, I also encountered the same problem as you, when using gMl-model-q4_0.gguf inference model on Android device (Qualcomm) GPU can...

no, i have met this problem, i just delete it, and it run with no problem, this extract_labels.py is just used to extract gt labels by teacher checkpoint, you can...

> If you are using OpenCV for video input, you could try the [`VideoCaptureAdapter`](https://www.scenedetect.com/docs/latest/api/backends.html#scenedetect.backends.opencv.VideoCaptureAdapter) which is intended for this use case. Could you let me know if that works for...

> just try to chat or send inference request it starts downloading related model automatically Thank you for your answer! I'm just wondering, if my network is not strong enough...