happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

hexagon: add support for linux on snapdragon (#21707) 

* hexagon: add support for debian on ex2

* hexagon: add -fvectotize to c/c++ cmake flags

* hexagon: remove trailing white space

* update onboarding steps

* hexagon: update linux setup documentation

* hexagon: update intallation scripts

* Hexagon: update docs

* hexagon: update onboarding scripts

---------

Co-authored-by: Zack Li <zackli@qti.qualcomm.com>
This commit is contained in:
Todor Boinovski 2026-04-10 15:57:23 -07:00 committed by GitHub
parent 9aa2807769
commit 81069a808a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 105 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
cmake/arm64-linux-clang.cmake Normal file
View File

@ -0,0 +1,17 @@
set( CMAKE_SYSTEM_NAME Linux )
set( CMAKE_SYSTEM_PROCESSOR arm64 )
set( target aarch64-linux-gnu )
set( CMAKE_C_COMPILER clang )
set( CMAKE_CXX_COMPILER clang++ )
set( CMAKE_C_COMPILER_TARGET ${target} )
set( CMAKE_CXX_COMPILER_TARGET ${target} )
set( arch_c_flags "-march=armv8.7-a -fvectorize -ffp-model=fast -fno-finite-math-only" )
set( warn_c_flags "-Wno-format -Wno-unused-variable -Wno-unused-function -Wno-gnu-zero-variadic-macro-arguments" )
set( CMAKE_C_FLAGS_INIT "${arch_c_flags} ${warn_c_flags}" )
set( CMAKE_CXX_FLAGS_INIT "${arch_c_flags} ${warn_c_flags}" )

31
docs/backend/snapdragon/CMakeUserPresets.json
View File

@ -52,10 +52,39 @@
}
},
{
"name": "arm64-linux-snapdragon",
"hidden": true,
"architecture": { "value": "arm64", "strategy": "external" },
"toolset": { "value": "host=x86_64", "strategy": "external" },
"cacheVariables": {
"CMAKE_TOOLCHAIN_FILE": "cmake/arm64-linux-clang.cmake",
"CMAKE_C_FLAGS": "-march=armv8 -fno-finite-math-only -flto -D_GNU_SOURCE",
"CMAKE_CXX_FLAGS": "-march=armv8 -fno-finite-math-only -flto -D_GNU_SOURCE",
"CMAKE_C_FLAGS_RELEASE": "-O3 -DNDEBUG",
"CMAKE_CXX_FLAGS_RELEASE": "-O3 -DNDEBUG",
"CMAKE_C_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
"CMAKE_CXX_FLAGS_RELWITHDEBINFO": "-O3 -DNDEBUG -g",
"CMAKE_PREFIX_PATH": "$env{OPENCL_SDK_ROOT}",
"HEXAGON_SDK_ROOT": "$env{HEXAGON_SDK_ROOT}",
"HEXAGON_TOOLS_ROOT": "$env{HEXAGON_TOOLS_ROOT}",
"PREBUILT_LIB_DIR": "linux_aarch64",
"GGML_OPENMP": "OFF",
"GGML_LLAMAFILE": "OFF",
"GGML_OPENCL": "OFF",
"GGML_HEXAGON": "ON",
"GGML_HEXAGON_FP32_QUANTIZE_GROUP_SIZE": "128",
"LLAMA_OPENSSL": "OFF"
}
},
{ "name": "arm64-android-snapdragon-debug" , "inherits": [ "base", "arm64-android-snapdragon", "debug" ] },
{ "name": "arm64-android-snapdragon-release", "inherits": [ "base", "arm64-android-snapdragon", "release" ] },
{ "name": "arm64-windows-snapdragon-debug" , "inherits": [ "base", "arm64-windows-snapdragon", "debug" ] },
{ "name": "arm64-windows-snapdragon-release", "inherits": [ "base", "arm64-windows-snapdragon", "release" ] }
{ "name": "arm64-windows-snapdragon-release", "inherits": [ "base", "arm64-windows-snapdragon", "release" ] },
{ "name": "arm64-linux-snapdragon-debug" , "inherits": [ "base", "arm64-linux-snapdragon", "debug" ] },
{ "name": "arm64-linux-snapdragon-release", "inherits": [ "base", "arm64-linux-snapdragon", "release" ] }
]
}

58
docs/backend/snapdragon/linux.md Normal file
View File

@ -0,0 +1,58 @@
# Snapdragon-based Linux devices
## Docker Setup
The easiest way to build llama.cpp for a Snapdragon-based Linux device is using the toolchain Docker image (see [github.com/snapdragon-toolchain](https://github.com/snapdragon-toolchain)).
This image includes OpenCL SDK, Hexagon SDK, CMake, and the ARM64 Linux cross-compilation toolchain.
Cross-compilation is supported on **Linux X86** hosts. The resulting binaries are deployed to and run on the target **Qualcomm Snapdragon ARM64 Linux** device.
```
~/src/llama.cpp$ docker run -it -u $(id -u):$(id -g) --volume $(pwd):/workspace --platform linux/amd64 ghcr.io/snapdragon-toolchain/arm64-linux:v0.1
[d]/> cd /workspace
```
Note: The rest of the **Linux** build process assumes that you're running inside the toolchain container.
## How to Build
Let's build llama.cpp with CPU, OpenCL, and Hexagon backends via CMake presets:
```
[d]/workspace> cp docs/backend/snapdragon/CMakeUserPresets.json .
[d]/workspace> cmake --preset arm64-linux-snapdragon-release -B build-snapdragon
[d]/workspace> cmake --build build-snapdragon -j $(nproc)
```
To generate an installable "package" simply use cmake --install, then zip it:
```
[d]/workspace> cmake --install build-snapdragon --prefix pkg-snapdragon
[d]/workspace> zip -r pkg-snapdragon.zip pkg-snapdragon
```
## How to Install
For this step, you will deploy the built binaries and libraries to the target Linux device. Transfer `pkg-snapdragon.zip` to the target device, then unzip it and set up the environment variables:
```
$ unzip pkg-snapdragon.zip
$ cd pkg-snapdragon
$ export LD_LIBRARY_PATH=./lib
$ export ADSP_LIBRARY_PATH=./lib
```
At this point, you should also download some models onto the device:
```
$ wget https://huggingface.co/bartowski/Llama-3.2-3B-Instruct-GGUF/resolve/main/Llama-3.2-3B-Instruct-Q4_0.gguf
```
## How to Run
Next, since we have setup the environment variables, we can run the llama-cli with the Hexagon backends:
```
$ ./bin/llama-cli -m Llama-3.2-3B-Instruct-Q4_0.gguf --device HTP0 -ngl 99 -p "what is the most popular cookie in the world?"
```