diff --git a/docs/android.md b/docs/android.md index cec4358d9..320b62240 100644 --- a/docs/android.md +++ b/docs/android.md @@ -2,55 +2,82 @@ # Android ## Build on Android using Termux -[Termux](https://github.com/termux/termux-app#installation) is a method to execute `llama.cpp` on an Android device (no root required). -``` -apt update && apt upgrade -y -apt install git make cmake -``` -It's recommended to move your model inside the `~/` directory for best performance: -``` -cd storage/downloads -mv model.gguf ~/ -``` +[Termux](https://termux.dev/en/) is an Android terminal emulator and Linux environment app (no root required). As of writing, Termux is available experimentally in the Google Play Store; otherwise, it may be obtained directly from the project repo or on F-Droid. -[Get the code](https://github.com/ggerganov/llama.cpp#get-the-code) & [follow the Linux build instructions](https://github.com/ggerganov/llama.cpp#build) to build `llama.cpp`. - -## Building the Project using Android NDK -Obtain the [Android NDK](https://developer.android.com/ndk) and then build with CMake. - -Execute the following commands on your computer to avoid downloading the NDK to your mobile. Alternatively, you can also do this in Termux: -``` -$ mkdir build-android -$ cd build-android -$ export NDK= -$ cmake -DCMAKE_TOOLCHAIN_FILE=$NDK/build/cmake/android.toolchain.cmake -DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=android-23 -DCMAKE_C_FLAGS=-march=armv8.4a+dotprod .. -$ make -``` - -Install [termux](https://github.com/termux/termux-app#installation) on your device and run `termux-setup-storage` to get access to your SD card (if Android 11+ then run the command twice). - -Finally, copy these built `llama` binaries and the model file to your device storage. Because the file permissions in the Android sdcard cannot be changed, you can copy the executable files to the `/data/data/com.termux/files/home/bin` path, and then execute the following commands in Termux to add executable permission: - -(Assumed that you have pushed the built executable files to the /sdcard/llama.cpp/bin path using `adb push`) -``` -$cp -r /sdcard/llama.cpp/bin /data/data/com.termux/files/home/ -$cd /data/data/com.termux/files/home/bin -$chmod +x ./* -``` - -Download model [llama-2-7b-chat.Q4_K_M.gguf](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/blob/main/llama-2-7b-chat.Q4_K_M.gguf), and push it to `/sdcard/llama.cpp/`, then move it to `/data/data/com.termux/files/home/model/` +With Termux, you can install and run `llama.cpp` as if the environment were Linux. Once in the Termux shell: ``` -$mv /sdcard/llama.cpp/llama-2-7b-chat.Q4_K_M.gguf /data/data/com.termux/files/home/model/ +$ apt update && apt upgrade -y +$ apt install git cmake ``` -Now, you can start chatting: +Then, follow the [build instructions](https://github.com/ggerganov/llama.cpp/blob/master/docs/build.md), specifically for CMake. + +Once the binaries are built, download your model of choice (e.g., from Hugging Face). It's recommended to place it in the `~/` directory for best performance: + ``` -$cd /data/data/com.termux/files/home/bin -$./llama-cli -m ../model/llama-2-7b-chat.Q4_K_M.gguf -n 128 -cml +$ curl -L {model-url} -o ~/{model}.gguf ``` -Here's a demo of an interactive session running on Pixel 5 phone: +Then, if you are not already in the repo directory, `cd` into `llama.cpp` and: + +``` +$ ./build/bin/llama-simple -m ~/{model}.gguf -c {context-size} -p "{your-prompt}" +``` + +Here, we show `llama-simple`, but any of the executables under `examples` should work, in theory. Be sure to set `context-size` to a reasonable number (say, 4096) to start with; otherwise, memory could spike and kill your terminal. + +To see what it might look like visually, here's an old demo of an interactive session running on a Pixel 5 phone: https://user-images.githubusercontent.com/271616/225014776-1d567049-ad71-4ef2-b050-55b0b3b9274c.mp4 + +## Cross-compile using Android NDK +It's possible to build `llama.cpp` for Android on your host system via CMake and the Android NDK. If you are interested in this path, ensure you already have an environment prepared to cross-compile programs for Android (i.e., install the Android SDK). Note that, unlike desktop environments, the Android environment ships with a limited set of native libraries, and so only those libraries are available to CMake when building with the Android NDK (see: https://developer.android.com/ndk/guides/stable_apis.) + +Once you're ready and have cloned `llama.cpp`, invoke the following in the project directory: + +``` +$ cmake \ + -DCMAKE_TOOLCHAIN_FILE=$ANDROID_NDK/build/cmake/android.toolchain.cmake \ + -DANDROID_ABI=arm64-v8a \ + -DANDROID_PLATFORM=android-28 \ + -DCMAKE_C_FLAGS="-march=armv8.7a" \ + -DCMAKE_CXX_FLAGS="-march=armv8.7a" \ + -DGGML_OPENMP=OFF \ + -DGGML_LLAMAFILE=OFF \ + -B build-android +``` + +Notes: + - While later versions of Android NDK ship with OpenMP, it must still be installed by CMake as a dependency, which is not supported at this time + - `llamafile` does not appear to support Android devices (see: https://github.com/Mozilla-Ocho/llamafile/issues/325) + +The above command should configure `llama.cpp` with the most performant options for modern devices. Even if your device is not running `armv8.7a`, `llama.cpp` includes runtime checks for available CPU features it can use. + +Feel free to adjust the Android ABI for your target. Once the project is configured: + +``` +$ cmake --build build-android --config Release -j{n} +$ cmake --install build-android --prefix {install-dir} --config Release +``` + +After installing, go ahead and download the model of your choice to your host system. Then: + +``` +$ adb shell "mkdir /data/local/tmp/llama.cpp" +$ adb push {install-dir} /data/local/tmp/llama.cpp/ +$ adb push {model}.gguf /data/local/tmp/llama.cpp/ +$ adb shell +``` + +In the `adb shell`: + +``` +$ cd /data/local/tmp/llama.cpp +$ LD_LIBRARY_PATH=lib ./bin/llama-simple -m {model}.gguf -c {context-size} -p "{your-prompt}" +``` + +That's it! + +Be aware that Android will not find the library path `lib` on its own, so we must specify `LD_LIBRARY_PATH` in order to run the installed executables. Android does support `RPATH` in later API levels, so this could change in the future. Refer to the previous section for information about `context-size` (very important!) and running other `examples`. diff --git a/ggml/src/CMakeLists.txt b/ggml/src/CMakeLists.txt index 286bec255..03cff4a99 100644 --- a/ggml/src/CMakeLists.txt +++ b/ggml/src/CMakeLists.txt @@ -1361,6 +1361,10 @@ if (MATH_LIBRARY) endif() endif() +if (CMAKE_SYSTEM_NAME MATCHES "Android") + list(APPEND GGML_EXTRA_LIBS_PRIVATE dl) # Must be linked explicitly +endif() + list(REMOVE_DUPLICATES GGML_EXTRA_LIBS_PRIVATE) list(REMOVE_DUPLICATES GGML_EXTRA_LIBS_PUBLIC) target_link_libraries(ggml PRIVATE ${GGML_EXTRA_LIBS_PRIVATE} PUBLIC ${GGML_EXTRA_LIBS_PUBLIC})