BrutalCoding

I can't recall whether I had purposely changed the minimum Android version due to something. Thus, there's a good chance that I can lower it to make it compatible with...

Yeah I was reading some comments from the authors of gemma.cpp on HN (HackerNews), and noticed some mentions of this being supported in llama.cpp too. I haven't tried their model...

Status update time! **Good news:** - Fixed compiler issues, code been migrated to llama_decode etc 😄 - Gemma works **Bad news** - I lied, kinda. I did migrate the code,...

Hi, Sorry, I don't have an answer ready yet, just wanted to let you know I've seen your question. I'd like to say that I'll get back to you soon...

I would suggest to not include big files as assets, because of the following (on top of my head) issues: - Compile time increases due to asset files being copied...

Hi there, No, I did not use a specific model to achieve this. The one you suggested should work just as fast, but I remember that one of my commits...

Heya, sorry to hear that. This is the file that the app seems to be missing on your device: https://github.com/android/src/main/jniLibs/arm64-v8a/libllama.so As seen from the file location, it is located in...

> I'm having the same issue. Your comment makes sense and i can confirm my emulator on my windows PC is configured to run with the system image x86_64. The...

> Yes when you set up an emulator you have to choose a system image. There I had to choose some Android API with x86_64 (since arm64-v8a doesn't work). I...

@escottgoodwin @d-kls can you pull the latest changes and give it a try? I have included Android x86_64 support and synced upstream with llama.cpp. Let me know if you're still...