Skip to content

Commit f1af42f

Browse files
authored
Update building for Android (#9672)
* docs : clarify building Android on Termux * docs : update building Android on Termux * docs : add cross-compiling for Android * cmake : link dl explicitly for Android
1 parent 6279dac commit f1af42f

File tree

2 files changed

+59
-28
lines changed

2 files changed

+59
-28
lines changed

docs/android.md

Lines changed: 55 additions & 28 deletions
Original file line numberDiff line numberDiff line change
@@ -2,55 +2,82 @@
22
# Android
33

44
## Build on Android using Termux
5-
[Termux](https://github.com/termux/termux-app#installation) is a method to execute `llama.cpp` on an Android device (no root required).
5+
6+
[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.
7+
8+
With Termux, you can install and run `llama.cpp` as if the environment were Linux. Once in the Termux shell:
9+
10+
```
11+
$ apt update && apt upgrade -y
12+
$ apt install git cmake
13+
```
14+
15+
Then, follow the [build instructions](https://github.com/ggerganov/llama.cpp/blob/master/docs/build.md), specifically for CMake.
16+
17+
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:
18+
619
```
7-
apt update && apt upgrade -y
8-
apt install git make cmake
20+
$ curl -L {model-url} -o ~/{model}.gguf
921
```
1022

11-
It's recommended to move your model inside the `~/` directory for best performance:
23+
Then, if you are not already in the repo directory, `cd` into `llama.cpp` and:
24+
1225
```
13-
cd storage/downloads
14-
mv model.gguf ~/
26+
$ ./build/bin/llama-simple -m ~/{model}.gguf -c {context-size} -p "{your-prompt}"
1527
```
1628

17-
[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`.
29+
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.
30+
31+
To see what it might look like visually, here's an old demo of an interactive session running on a Pixel 5 phone:
32+
33+
https://user-images.githubusercontent.com/271616/225014776-1d567049-ad71-4ef2-b050-55b0b3b9274c.mp4
34+
35+
## Cross-compile using Android NDK
36+
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.)
1837

19-
## Building the Project using Android NDK
20-
Obtain the [Android NDK](https://developer.android.com/ndk) and then build with CMake.
38+
Once you're ready and have cloned `llama.cpp`, invoke the following in the project directory:
2139

22-
Execute the following commands on your computer to avoid downloading the NDK to your mobile. Alternatively, you can also do this in Termux:
2340
```
24-
$ mkdir build-android
25-
$ cd build-android
26-
$ export NDK=<your_ndk_directory>
27-
$ 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 ..
28-
$ make
41+
$ cmake \
42+
-DCMAKE_TOOLCHAIN_FILE=$ANDROID_NDK/build/cmake/android.toolchain.cmake \
43+
-DANDROID_ABI=arm64-v8a \
44+
-DANDROID_PLATFORM=android-28 \
45+
-DCMAKE_C_FLAGS="-march=armv8.7a" \
46+
-DCMAKE_CXX_FLAGS="-march=armv8.7a" \
47+
-DGGML_OPENMP=OFF \
48+
-DGGML_LLAMAFILE=OFF \
49+
-B build-android
2950
```
3051

31-
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).
52+
Notes:
53+
- 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
54+
- `llamafile` does not appear to support Android devices (see: https://github.com/Mozilla-Ocho/llamafile/issues/325)
55+
56+
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.
3257

33-
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:
58+
Feel free to adjust the Android ABI for your target. Once the project is configured:
3459

35-
(Assumed that you have pushed the built executable files to the /sdcard/llama.cpp/bin path using `adb push`)
3660
```
37-
$cp -r /sdcard/llama.cpp/bin /data/data/com.termux/files/home/
38-
$cd /data/data/com.termux/files/home/bin
39-
$chmod +x ./*
61+
$ cmake --build build-android --config Release -j{n}
62+
$ cmake --install build-android --prefix {install-dir} --config Release
4063
```
4164

42-
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/`
65+
After installing, go ahead and download the model of your choice to your host system. Then:
4366

4467
```
45-
$mv /sdcard/llama.cpp/llama-2-7b-chat.Q4_K_M.gguf /data/data/com.termux/files/home/model/
68+
$ adb shell "mkdir /data/local/tmp/llama.cpp"
69+
$ adb push {install-dir} /data/local/tmp/llama.cpp/
70+
$ adb push {model}.gguf /data/local/tmp/llama.cpp/
71+
$ adb shell
4672
```
4773

48-
Now, you can start chatting:
74+
In the `adb shell`:
75+
4976
```
50-
$cd /data/data/com.termux/files/home/bin
51-
$./llama-cli -m ../model/llama-2-7b-chat.Q4_K_M.gguf -n 128 -cml
77+
$ cd /data/local/tmp/llama.cpp
78+
$ LD_LIBRARY_PATH=lib ./bin/llama-simple -m {model}.gguf -c {context-size} -p "{your-prompt}"
5279
```
5380

54-
Here's a demo of an interactive session running on Pixel 5 phone:
81+
That's it!
5582

56-
https://user-images.githubusercontent.com/271616/225014776-1d567049-ad71-4ef2-b050-55b0b3b9274c.mp4
83+
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`.

ggml/src/CMakeLists.txt

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1361,6 +1361,10 @@ if (MATH_LIBRARY)
13611361
endif()
13621362
endif()
13631363

1364+
if (CMAKE_SYSTEM_NAME MATCHES "Android")
1365+
list(APPEND GGML_EXTRA_LIBS_PRIVATE dl) # Must be linked explicitly
1366+
endif()
1367+
13641368
list(REMOVE_DUPLICATES GGML_EXTRA_LIBS_PRIVATE)
13651369
list(REMOVE_DUPLICATES GGML_EXTRA_LIBS_PUBLIC)
13661370
target_link_libraries(ggml PRIVATE ${GGML_EXTRA_LIBS_PRIVATE} PUBLIC ${GGML_EXTRA_LIBS_PUBLIC})

0 commit comments

Comments
 (0)