Steps to test llama.cpp inference on Android:

1. Install Termux from the PlayStore and open it.
2. Run apt update
3. Run apt remove vulkan-loader-generic
4. Run apt install git cmake vulkan-tools vulkan-headers shaderc vulkan-loader-android
5. Run vulkaninfo --summary: This should show the driver and gpu information. If it's the stock driver, it shouldn't mention Mesa.
6. git clone the repo inside termux and cd into it.

git clone https://github.com/makaveli10/qvac-ext-lib-llama.cpp.git
git checkout lora-finetuning

make sure to checkout the lora-finetuning branch
7. Configure the vulkan backend build with cmake -B build -DGGML_VULKAN=1
8. Build it with cmake --build build --config Debug -j2
9. Run termux-setup-storage and give storage permissions to termux.
10. Outside termux, download a model on the phone, click on it and select to open it with termux. Download the model from here: https://huggingface.co/prithivMLmods/Qwen3-0.6B-GGUF/tree/main i.e. download Qwen3_0.6B.Q8_0.gguf
11. Click "Open Directory" on the prompt.
12. The model should now be reachable inside termux in the ~/downloads directory.
13. For finetunine 8 bit Qwen:

./build/bin/llama-finetune-lora -m Qwen3_0.6B.Q8_0.gguf -f trump.txt -c 256 -b 256 -ub 256 -ngl 999

trump.txt dataset: https://github.com/user-attachments/files/21859494/trump.txt

For testing I'll reference the updated README: https://github.com/tetherto/qvac-ext-lib-llama.cpp/blob/bc7dd9f9288222394da37eac3d7adf71d409ad83/examples/training/README.md#using-trained-adapters

./build/bin/llama-cli -m Qwen3_0.6B.Q8_0.gguf --lora trained-lora-adapter.gguf -if -p "What is your favorite pokemon?" -ngl 999

command we used for testing

Looks like there are some CI failures also related to these changes - see https://github.com/tetherto/qvac-ext-lib-llama.cpp/actions/runs/17076253696/job/48418341198?pr=5 for example:

/__w/qvac-ext-lib-llama.cpp/qvac-ext-lib-llama.cpp/src/llama-lora-training.cpp:293:29: error: the address of 'ggml_tensor::name' will never be NULL [-Werror=address]
  293 |     if (!tensor || !tensor->name) {
      |                     ~~~~~~~~^~~~

Fine Tuning attempt on Pixel 9 Pro Fold Evidence below.

Please note the 27.5 hours estimated completion time...

@JamieBohannaWebDev On our side, I think for a test we ran it with 10-20% of the data. Took much less time. Also we have checkpoint saving resuming integration going on which would allows us to train in bursts by saving a checkpoint and resuming later from the same point.

@JamieBohannaWebDev Did we test the output with some prompts after the completion of the fine-tuned model? (before vs. after)

The current CI failures seem unrelated to the changes here, both are failing with:

No suitable Dawn artifact found!