vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

build: drop implicit . from cmake config command

Browse source
This commit is contained in:
Olivier Chafik 2024-04-28 17:59:57 +01:00
parent 3e8869697c
commit dc5d7fee9d
10 changed files with 25 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.devops/main-intel.Dockerfile
View file

@ -14,7 +14,7 @@ RUN if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
echo "LLAMA_SYCL_F16 is set" && \
export OPT_SYCL_F16="-DLLAMA_SYCL_F16=ON"; \
fi && \
cmake . -B build -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx ${OPT_SYCL_F16} && \
cmake -B build -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx ${OPT_SYCL_F16} && \
cmake --build build --target main
FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime

2
.devops/main-vulkan.Dockerfile
View file

@ -14,7 +14,7 @@ RUN wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key
# Build it
WORKDIR /app
COPY . .
RUN cmake . -B build -DLLAMA_VULKAN=1 && \
RUN cmake -B build -DLLAMA_VULKAN=1 && \
cmake --build build --target main
# Clean up

2
.devops/server-intel.Dockerfile
View file

@ -14,7 +14,7 @@ RUN if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
echo "LLAMA_SYCL_F16 is set" && \
export OPT_SYCL_F16="-DLLAMA_SYCL_F16=ON"; \
fi && \
cmake . -B build -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON ${OPT_SYCL_F16} && \
cmake -B build -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON ${OPT_SYCL_F16} && \
cmake --build build --target server
FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime

2
.devops/server-vulkan.Dockerfile
View file

@ -18,7 +18,7 @@ RUN apt-get update && \
# Build it
WORKDIR /app
COPY . .
RUN cmake . -B build -DLLAMA_VULKAN=1 -DLLAMA_CURL=1 && \
RUN cmake -B build -DLLAMA_VULKAN=1 -DLLAMA_CURL=1 && \
cmake --build build --target server
# Clean up

2
.github/workflows/bench.yml vendored
View file

@ -96,7 +96,7 @@ jobs:
id: cmake_build
run: |
set -eux
cmake . -B build \
cmake -B build \
-DLLAMA_NATIVE=OFF \
-DLLAMA_BUILD_SERVER=ON \
-DLLAMA_CURL=ON \

4
.github/workflows/server.yml vendored
View file

@ -94,7 +94,7 @@ jobs:
- name: Build
id: cmake_build
run: |
cmake . -B build \
cmake -B build \
-DLLAMA_NATIVE=OFF \
-DLLAMA_BUILD_SERVER=ON \
-DLLAMA_CURL=ON \
@ -141,7 +141,7 @@ jobs:
- name: Build
id: cmake_build
run: |
cmake . -B build -DLLAMA_CURL=ON -DCURL_LIBRARY="$env:RUNNER_TEMP/libcurl/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:RUNNER_TEMP/libcurl/include"
cmake -B build -DLLAMA_CURL=ON -DCURL_LIBRARY="$env:RUNNER_TEMP/libcurl/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:RUNNER_TEMP/libcurl/include"
cmake --build build -j ${env:NUMBER_OF_PROCESSORS} --target server
- name: Python setup

8
README-sycl.md
View file

@ -228,10 +228,10 @@ source /opt/intel/oneapi/setvars.sh
# Build LLAMA with MKL BLAS acceleration for intel GPU
# Option 1: Use FP32 (recommended for better performance in most cases)
cmake . -B build -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
cmake -B build -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
# Option 2: Use FP16
cmake . -B build -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON
cmake -B build -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON
# build all binary
cmake --build build -j -v
@ -248,10 +248,10 @@ export CPLUS_INCLUDE_DIR=/path/to/oneMKL/include:$CPLUS_INCLUDE_DIR
# Build LLAMA with Nvidia BLAS acceleration through SYCL
# Option 1: Use FP32 (recommended for better performance in most cases)
cmake . -B build -DLLAMA_SYCL=ON -DLLAMA_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
cmake -B build -DLLAMA_SYCL=ON -DLLAMA_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
# Option 2: Use FP16
cmake . -B build -DLLAMA_SYCL=ON -DLLAMA_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON
cmake -B build -DLLAMA_SYCL=ON -DLLAMA_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON
# build all binary
cmake --build build -j -v

20
README.md
View file

@ -321,7 +321,7 @@ In order to build llama.cpp you have three different options.
- Using `CMake`:
```bash
cmake . -B build # Note: add -DCMAKE_BUILD_TYPE=Debug here for debug builds
cmake -B build # Note: add -DCMAKE_BUILD_TYPE=Debug here for debug builds
cmake --build build
```
@ -436,7 +436,7 @@ Building the program with BLAS support may lead to some performance improvements
- Using `CMake` on Linux:
```bash
cmake . -B build -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
cmake -B build -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
cmake --build build
```
@ -458,7 +458,7 @@ Building the program with BLAS support may lead to some performance improvements
By default, `LLAMA_BLAS_VENDOR` is set to `Generic`, so if you already sourced intel environment script and assign `-DLLAMA_BLAS=ON` in cmake, the mkl version of Blas will automatically been selected. Otherwise please install oneAPI and follow the below steps:
```bash
source /opt/intel/oneapi/setvars.sh # You can skip this step if in oneapi-basekit docker image, only required for manual installation
cmake . -B build -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=Intel10_64lp -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_NATIVE=ON
cmake -B build -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=Intel10_64lp -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_NATIVE=ON
cmake --build build
```
@ -480,7 +480,7 @@ Building the program with BLAS support may lead to some performance improvements
- Using `CMake`:
```bash
cmake . -B build -DLLAMA_CUDA=ON
cmake -B build -DLLAMA_CUDA=ON
cmake --build build
```
@ -556,7 +556,7 @@ Building the program with BLAS support may lead to some performance improvements
```sh
git clone --recurse-submodules https://github.com/KhronosGroup/OpenCL-SDK.git
cd OpenCL-SDK
cmake . -B build -DBUILD_DOCS=OFF \
cmake -B build -DBUILD_DOCS=OFF \
-DBUILD_EXAMPLES=OFF \
-DBUILD_TESTING=OFF \
-DOPENCL_SDK_BUILD_SAMPLES=OFF \
@ -585,7 +585,7 @@ Building the program with BLAS support may lead to some performance improvements
set OPENCL_SDK_ROOT="C:/OpenCL-SDK-v2023.04.17-Win-x64"
git clone https://github.com/CNugteren/CLBlast.git
cd CLBlast
cmake . -B build -DBUILD_SHARED_LIBS=OFF -DOVERRIDE_MSVC_FLAGS_TO_MT=OFF -DTUNERS=OFF -DOPENCL_ROOT=%OPENCL_SDK_ROOT% -G "Visual Studio 17 2022" -A x64
cmake -B build -DBUILD_SHARED_LIBS=OFF -DOVERRIDE_MSVC_FLAGS_TO_MT=OFF -DTUNERS=OFF -DOPENCL_ROOT=%OPENCL_SDK_ROOT% -G "Visual Studio 17 2022" -A x64
cmake --build build --config Release
cmake --install build --prefix C:/CLBlast
```
@ -598,7 +598,7 @@ Building the program with BLAS support may lead to some performance improvements
```sh
git clone https://github.com/CNugteren/CLBlast.git
cd CLBlast
cmake . -B build -DBUILD_SHARED_LIBS=OFF -DTUNERS=OFF
cmake -B build -DBUILD_SHARED_LIBS=OFF -DTUNERS=OFF
cmake --build build
cmake --install build --prefix /some/path
```
@ -614,7 +614,7 @@ Building the program with BLAS support may lead to some performance improvements
```
- CMake (Unix):
```sh
cmake . -B build -DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
cmake -B build -DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
cmake --build build
```
- CMake (Windows):
@ -622,7 +622,7 @@ Building the program with BLAS support may lead to some performance improvements
set CL_BLAST_CMAKE_PKG="C:/CLBlast/lib/cmake/CLBlast"
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
cmake . -B build -DBUILD_SHARED_LIBS=OFF -DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH=%CL_BLAST_CMAKE_PKG% -G "Visual Studio 17 2022" -A x64
cmake -B build -DBUILD_SHARED_LIBS=OFF -DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH=%CL_BLAST_CMAKE_PKG% -G "Visual Studio 17 2022" -A x64
cmake --build build --config Release
cmake --install build --prefix C:/LlamaCPP
```
@ -680,7 +680,7 @@ Building the program with BLAS support may lead to some performance improvements
Then, build llama.cpp using the cmake command below:
```bash
cmake . -B build -DLLAMA_VULKAN=1
cmake -B build -DLLAMA_VULKAN=1
cmake --build build
# Test the output binary (with "-ngl 33" to offload all layers to GPU)
./bin/main -m "PATH_TO_MODEL" -p "Hi you how are you" -n 50 -e -ngl 33 -t 4

4
examples/main-cmake-pkg/README.md
View file

@ -17,7 +17,7 @@ In this case, CLBlast was already installed so the CMake package is referenced i
```cmd
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
cmake . -B build -DBUILD_SHARED_LIBS=OFF -DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH=C:/CLBlast/lib/cmake/CLBlast -G "Visual Studio 17 2022" -A x64
cmake -B build -DBUILD_SHARED_LIBS=OFF -DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH=C:/CLBlast/lib/cmake/CLBlast -G "Visual Studio 17 2022" -A x64
cmake --build build --config Release
cmake --install build --prefix C:/LlamaCPP
```
@ -27,7 +27,7 @@ cmake --install build --prefix C:/LlamaCPP
```cmd
cd ..\examples\main-cmake-pkg
cmake . -B build -DBUILD_SHARED_LIBS=OFF -DCMAKE_PREFIX_PATH="C:/CLBlast/lib/cmake/CLBlast;C:/LlamaCPP/lib/cmake/Llama" -G "Visual Studio 17 2022" -A x64
cmake -B build -DBUILD_SHARED_LIBS=OFF -DCMAKE_PREFIX_PATH="C:/CLBlast/lib/cmake/CLBlast;C:/LlamaCPP/lib/cmake/Llama" -G "Visual Studio 17 2022" -A x64
cmake --build build --config Release
cmake --install build --prefix C:/MyLlamaApp
```

4
examples/server/README.md
View file

@ -80,7 +80,7 @@ page cache before using this. See https://github.com/ggerganov/llama.cpp/issues/
- Using `CMake`:
```bash
cmake . -B build
cmake -B build
cmake --build build -t server
```
@ -102,7 +102,7 @@ page cache before using this. See https://github.com/ggerganov/llama.cpp/issues/
- Using `CMake`:
```bash
cmake . -B build -DLLAMA_SERVER_SSL=ON
cmake -B build -DLLAMA_SERVER_SSL=ON
cmake --build build -t server
```