root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

build(cmake): simplify instructions (cmake -B build && cmake --build build ...) (#6964)

Browse Source 
* readme: cmake . -B build && cmake --build build

* build: fix typo

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* build: drop implicit . from cmake config command

* build: remove another superfluous .

* build: update MinGW cmake commands

* Update README-sycl.md

Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com>

* build: reinstate --config Release as not the default w/ some generators + document how to build Debug

* build: revert more --config Release

* build: nit / remove -H from cmake example

* build: reword debug instructions around single/multi config split

---------

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com>
This commit is contained in:
Olivier Chafik 2024-04-29 17:02:45 +01:00 committed by GitHub
parent d2c898f746
commit b8a7a5a90f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
10 changed files with 91 additions and 110 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
.devops/main-intel.Dockerfile
View File

@ -10,14 +10,12 @@ WORKDIR /app
COPY . . COPY . .
RUN mkdir build && \ RUN if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
cd build && \
if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
echo "LLAMA_SYCL_F16 is set" && \ echo "LLAMA_SYCL_F16 is set" && \
export OPT_SYCL_F16="-DLLAMA_SYCL_F16=ON"; \ export OPT_SYCL_F16="-DLLAMA_SYCL_F16=ON"; \
fi && \ fi && \
cmake .. -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 ${OPT_SYCL_F16} && \
cmake --build . --config Release --target main cmake --build build --config Release --target main
FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime

6
.devops/main-vulkan.Dockerfile
View File

@ -14,10 +14,8 @@ RUN wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key
# Build it # Build it
WORKDIR /app WORKDIR /app
COPY . . COPY . .
RUN mkdir build && \ RUN cmake -B build -DLLAMA_VULKAN=1 && \
cd build && \ cmake --build build --config Release --target main
cmake .. -DLLAMA_VULKAN=1 && \
cmake --build . --config Release --target main
# Clean up # Clean up
WORKDIR / WORKDIR /

8
.devops/server-intel.Dockerfile
View File

@ -10,14 +10,12 @@ WORKDIR /app
COPY . . COPY . .
RUN mkdir build && \ RUN if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
cd build && \
if [ "${LLAMA_SYCL_F16}" = "ON" ]; then \
echo "LLAMA_SYCL_F16 is set" && \ echo "LLAMA_SYCL_F16 is set" && \
export OPT_SYCL_F16="-DLLAMA_SYCL_F16=ON"; \ export OPT_SYCL_F16="-DLLAMA_SYCL_F16=ON"; \
fi && \ fi && \
cmake .. -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 ${OPT_SYCL_F16} && \
cmake --build . --config Release --target server cmake --build build --config Release --target server
FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime FROM intel/oneapi-basekit:$ONEAPI_VERSION as runtime

6
.devops/server-vulkan.Dockerfile
View File

@ -18,10 +18,8 @@ RUN apt-get update && \
# Build it # Build it
WORKDIR /app WORKDIR /app
COPY . . COPY . .
RUN mkdir build && \ RUN cmake -B build -DLLAMA_VULKAN=1 -DLLAMA_CURL=1 && \
cd build && \ cmake --build build --config Release --target server
cmake .. -DLLAMA_VULKAN=1 -DLLAMA_CURL=1 && \
cmake --build . --config Release --target server
# Clean up # Clean up
WORKDIR / WORKDIR /

6
.github/workflows/bench.yml vendored
View File

@ -96,9 +96,7 @@ jobs:
id: cmake_build id: cmake_build
run: | run: |
set -eux set -eux
mkdir build cmake -B build \
cd build
cmake .. \
-DLLAMA_NATIVE=OFF \ -DLLAMA_NATIVE=OFF \
-DLLAMA_BUILD_SERVER=ON \ -DLLAMA_BUILD_SERVER=ON \
-DLLAMA_CURL=ON \ -DLLAMA_CURL=ON \
@ -109,7 +107,7 @@ jobs:
-DLLAMA_FATAL_WARNINGS=OFF \ -DLLAMA_FATAL_WARNINGS=OFF \
-DLLAMA_ALL_WARNINGS=OFF \ -DLLAMA_ALL_WARNINGS=OFF \
-DCMAKE_BUILD_TYPE=Release; -DCMAKE_BUILD_TYPE=Release;
cmake --build . --config Release -j $(nproc) --target server cmake --build build --config Release -j $(nproc) --target server
- name: Download the dataset - name: Download the dataset
id: download_dataset id: download_dataset

12
.github/workflows/server.yml vendored
View File

@ -94,15 +94,13 @@ jobs:
- name: Build - name: Build
id: cmake_build id: cmake_build
run: | run: |
mkdir build cmake -B build \
cd build
cmake .. \
-DLLAMA_NATIVE=OFF \ -DLLAMA_NATIVE=OFF \
-DLLAMA_BUILD_SERVER=ON \ -DLLAMA_BUILD_SERVER=ON \
-DLLAMA_CURL=ON \ -DLLAMA_CURL=ON \
-DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \ -DCMAKE_BUILD_TYPE=${{ matrix.build_type }} \
-DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON ; -DLLAMA_SANITIZE_${{ matrix.sanitizer }}=ON ;
cmake --build . --config ${{ matrix.build_type }} -j $(nproc) --target server cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target server
- name: Tests - name: Tests
@ -143,10 +141,8 @@ jobs:
- name: Build - name: Build
id: cmake_build id: cmake_build
run: | run: |
mkdir build cmake -B build -DLLAMA_CURL=ON -DCURL_LIBRARY="$env:RUNNER_TEMP/libcurl/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:RUNNER_TEMP/libcurl/include"
cd build cmake --build build --config Release -j ${env:NUMBER_OF_PROCESSORS} --target server
cmake .. -DLLAMA_CURL=ON -DCURL_LIBRARY="$env:RUNNER_TEMP/libcurl/lib/libcurl.dll.a" -DCURL_INCLUDE_DIR="$env:RUNNER_TEMP/libcurl/include"
cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS} --target server
- name: Python setup - name: Python setup
id: setup_python id: setup_python

31
README-sycl.md
View File

@ -185,9 +185,8 @@ Upon a successful installation, SYCL is enabled for the available intel devices,
```sh ```sh
git clone https://github.com/oneapi-src/oneMKL git clone https://github.com/oneapi-src/oneMKL
cd oneMKL cd oneMKL
mkdir -p buildWithCublas && cd buildWithCublas cmake -B buildWithCublas -DCMAKE_CXX_COMPILER=icpx -DCMAKE_C_COMPILER=icx -DENABLE_MKLGPU_BACKEND=OFF -DENABLE_MKLCPU_BACKEND=OFF -DENABLE_CUBLAS_BACKEND=ON -DTARGET_DOMAINS=blas
cmake ../ -DCMAKE_CXX_COMPILER=icpx -DCMAKE_C_COMPILER=icx -DENABLE_MKLGPU_BACKEND=OFF -DENABLE_MKLCPU_BACKEND=OFF -DENABLE_CUBLAS_BACKEND=ON -DTARGET_DOMAINS=blas cmake --build buildWithCublas --config Release
make
``` ```
@ -227,16 +226,15 @@ Similarly, user targeting Nvidia GPUs should expect at least one SYCL-CUDA devic
source /opt/intel/oneapi/setvars.sh source /opt/intel/oneapi/setvars.sh
# Build LLAMA with MKL BLAS acceleration for intel GPU # Build LLAMA with MKL BLAS acceleration for intel GPU
mkdir -p build && cd build
# Option 1: Use FP32 (recommended for better performance in most cases) # Option 1: Use FP32 (recommended for better performance in most cases)
cmake .. -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 # Option 2: Use FP16
cmake .. -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 # build all binary
cmake --build . --config Release -j -v cmake --build build --config Release -j -v
``` ```
#### Nvidia GPU #### Nvidia GPU
@ -248,16 +246,15 @@ export CPLUS_INCLUDE_DIR=/path/to/oneMKL/buildWithCublas/include:$CPLUS_INCLUDE_
export CPLUS_INCLUDE_DIR=/path/to/oneMKL/include:$CPLUS_INCLUDE_DIR export CPLUS_INCLUDE_DIR=/path/to/oneMKL/include:$CPLUS_INCLUDE_DIR
# Build LLAMA with Nvidia BLAS acceleration through SYCL # Build LLAMA with Nvidia BLAS acceleration through SYCL
mkdir -p build && cd build
# Option 1: Use FP32 (recommended for better performance in most cases) # Option 1: Use FP32 (recommended for better performance in most cases)
cmake .. -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 # Option 2: Use FP16
cmake .. -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 # build all binary
cmake --build . --config Release -j -v cmake --build build --config Release -j -v
``` ```
@ -412,17 +409,15 @@ b. Download & install mingw-w64 make for Windows provided by w64devkit
On the oneAPI command line window, step into the llama.cpp main directory and run the following: On the oneAPI command line window, step into the llama.cpp main directory and run the following:
``` ```
mkdir -p build
cd build
@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force @call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
# Option 1: Use FP32 (recommended for better performance in most cases) # Option 1: Use FP32 (recommended for better performance in most cases)
cmake -G "MinGW Makefiles" .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release cmake -B build -G "MinGW Makefiles" -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release
# Option 2: Or FP16 # Option 2: Or FP16
cmake -G "MinGW Makefiles" .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release -DLLAMA_SYCL_F16=ON cmake -B build -G "MinGW Makefiles" -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release -DLLAMA_SYCL_F16=ON
make -j cmake --build build --config Release -j
``` ```
Otherwise, run the `win-build-sycl.bat` wrapper which encapsulates the former instructions: Otherwise, run the `win-build-sycl.bat` wrapper which encapsulates the former instructions:

95
README.md
View File

@ -308,6 +308,8 @@ In order to build llama.cpp you have three different options.
make make
``` ```
**Note**: for `Debug` builds, run `make LLAMA_DEBUG=1`
- On Windows: - On Windows:
1. Download the latest fortran version of [w64devkit](https://github.com/skeeto/w64devkit/releases). 1. Download the latest fortran version of [w64devkit](https://github.com/skeeto/w64devkit/releases).
@ -322,12 +324,26 @@ In order to build llama.cpp you have three different options.
- Using `CMake`: - Using `CMake`:
```bash ```bash
mkdir build cmake -B build
cd build cmake --build build --config Release
cmake ..
cmake --build . --config Release
``` ```
**Note**: for `Debug` builds, there are two cases:
- Single-config generators (e.g. default = `Unix Makefiles`; note that they just ignore the `--config` flag):
```bash
cmake -B build -DCMAKE_BUILD_TYPE=Debug
cmake --build build
```
- Multi-config generators (`-G` param set to Visual Studio, XCode...):
```bash
cmake -B build -G "Xcode"
cmake --build build --config Debug
```
- Using `Zig` (version 0.11 or later): - Using `Zig` (version 0.11 or later):
Building for optimization levels and CPU features can be accomplished using standard build arguments, for example AVX2, FMA, F16C, Building for optimization levels and CPU features can be accomplished using standard build arguments, for example AVX2, FMA, F16C,
@ -439,10 +455,8 @@ Building the program with BLAS support may lead to some performance improvements
- Using `CMake` on Linux: - Using `CMake` on Linux:
```bash ```bash
mkdir build cmake -B build -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
cd build cmake --build build --config Release
cmake .. -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
cmake --build . --config Release
``` ```
- #### BLIS - #### BLIS
@ -462,11 +476,9 @@ Building the program with BLAS support may lead to some performance improvements
- Using manual oneAPI installation: - Using manual oneAPI installation:
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: 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 ```bash
mkdir build
cd build
source /opt/intel/oneapi/setvars.sh # You can skip this step if in oneapi-basekit docker image, only required for manual installation source /opt/intel/oneapi/setvars.sh # You can skip this step if in oneapi-basekit docker image, only required for manual installation
cmake .. -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 . --config Release cmake --build build --config Release
``` ```
- Using oneAPI docker image: - Using oneAPI docker image:
@ -487,10 +499,8 @@ Building the program with BLAS support may lead to some performance improvements
- Using `CMake`: - Using `CMake`:
```bash ```bash
mkdir build cmake -B build -DLLAMA_CUDA=ON
cd build cmake --build build --config Release
cmake .. -DLLAMA_CUDA=ON
cmake --build . --config Release
``` ```
The environment variable [`CUDA_VISIBLE_DEVICES`](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars) can be used to specify which GPU(s) will be used. The following compilation options are also available to tweak performance: The environment variable [`CUDA_VISIBLE_DEVICES`](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars) can be used to specify which GPU(s) will be used. The following compilation options are also available to tweak performance:
@ -517,8 +527,8 @@ Building the program with BLAS support may lead to some performance improvements
- Using `CMake` for Linux (assuming a gfx1030-compatible AMD GPU): - Using `CMake` for Linux (assuming a gfx1030-compatible AMD GPU):
```bash ```bash
CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++ \ CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++ \
cmake -H. -Bbuild -DLLAMA_HIPBLAS=ON -DAMDGPU_TARGETS=gfx1030 -DCMAKE_BUILD_TYPE=Release \ cmake -B build -DLLAMA_HIPBLAS=ON -DAMDGPU_TARGETS=gfx1030 -DCMAKE_BUILD_TYPE=Release \
&& cmake --build build -- -j 16 && cmake --build build --config Release -- -j 16
``` ```
On Linux it is also possible to use unified memory architecture (UMA) to share main memory between the CPU and integrated GPU by setting `-DLLAMA_HIP_UMA=ON"`. On Linux it is also possible to use unified memory architecture (UMA) to share main memory between the CPU and integrated GPU by setting `-DLLAMA_HIP_UMA=ON"`.
However, this hurts performance for non-integrated GPUs (but enables working with integrated GPUs). However, this hurts performance for non-integrated GPUs (but enables working with integrated GPUs).
@ -564,15 +574,14 @@ Building the program with BLAS support may lead to some performance improvements
```sh ```sh
git clone --recurse-submodules https://github.com/KhronosGroup/OpenCL-SDK.git git clone --recurse-submodules https://github.com/KhronosGroup/OpenCL-SDK.git
mkdir OpenCL-SDK/build cd OpenCL-SDK
cd OpenCL-SDK/build cmake -B build -DBUILD_DOCS=OFF \
cmake .. -DBUILD_DOCS=OFF \
-DBUILD_EXAMPLES=OFF \ -DBUILD_EXAMPLES=OFF \
-DBUILD_TESTING=OFF \ -DBUILD_TESTING=OFF \
-DOPENCL_SDK_BUILD_SAMPLES=OFF \ -DOPENCL_SDK_BUILD_SAMPLES=OFF \
-DOPENCL_SDK_TEST_SAMPLES=OFF -DOPENCL_SDK_TEST_SAMPLES=OFF
cmake --build . --config Release cmake --build build
cmake --install . --prefix /some/path cmake --install build --prefix /some/path
``` ```
</details> </details>
@ -594,23 +603,23 @@ Building the program with BLAS support may lead to some performance improvements
```cmd ```cmd
set OPENCL_SDK_ROOT="C:/OpenCL-SDK-v2023.04.17-Win-x64" set OPENCL_SDK_ROOT="C:/OpenCL-SDK-v2023.04.17-Win-x64"
git clone https://github.com/CNugteren/CLBlast.git git clone https://github.com/CNugteren/CLBlast.git
mkdir CLBlast\build cd CLBlast
cd CLBlast\build 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 .. -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 --build . --config Release cmake --install build --prefix C:/CLBlast
cmake --install . --prefix C:/CLBlast
``` ```
(note: `--config Release` at build time is the default and only relevant for Visual Studio builds - or multi-config Ninja builds)
- <details> - <details>
<summary>Unix:</summary> <summary>Unix:</summary>
```sh ```sh
git clone https://github.com/CNugteren/CLBlast.git git clone https://github.com/CNugteren/CLBlast.git
mkdir CLBlast/build cd CLBlast
cd CLBlast/build cmake -B build -DBUILD_SHARED_LIBS=OFF -DTUNERS=OFF
cmake .. -DBUILD_SHARED_LIBS=OFF -DTUNERS=OFF cmake --build build --config Release
cmake --build . --config Release cmake --install build --prefix /some/path
cmake --install . --prefix /some/path
``` ```
Where `/some/path` is where the built library will be installed (default is `/usr/local`). Where `/some/path` is where the built library will be installed (default is `/usr/local`).
@ -624,21 +633,17 @@ Building the program with BLAS support may lead to some performance improvements
``` ```
- CMake (Unix): - CMake (Unix):
```sh ```sh
mkdir build cmake -B build -DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
cd build cmake --build build --config Release
cmake .. -DLLAMA_CLBLAST=ON -DCLBlast_DIR=/some/path
cmake --build . --config Release
``` ```
- CMake (Windows): - CMake (Windows):
```cmd ```cmd
set CL_BLAST_CMAKE_PKG="C:/CLBlast/lib/cmake/CLBlast" set CL_BLAST_CMAKE_PKG="C:/CLBlast/lib/cmake/CLBlast"
git clone https://github.com/ggerganov/llama.cpp git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp cd llama.cpp
mkdir build cmake -B build -DBUILD_SHARED_LIBS=OFF -DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH=%CL_BLAST_CMAKE_PKG% -G "Visual Studio 17 2022" -A x64
cd build cmake --build build --config Release
cmake .. -DBUILD_SHARED_LIBS=OFF -DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH=%CL_BLAST_CMAKE_PKG% -G "Visual Studio 17 2022" -A x64 cmake --install build --prefix C:/LlamaCPP
cmake --build . --config Release
cmake --install . --prefix C:/LlamaCPP
``` ```
##### Running Llama with CLBlast ##### Running Llama with CLBlast
@ -694,10 +699,8 @@ Building the program with BLAS support may lead to some performance improvements
Then, build llama.cpp using the cmake command below: Then, build llama.cpp using the cmake command below:
```bash ```bash
mkdir -p build cmake -B build -DLLAMA_VULKAN=1
cd build cmake --build build --config Release
cmake .. -DLLAMA_VULKAN=1
cmake --build . --config Release
# Test the output binary (with "-ngl 33" to offload all layers to GPU) # 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 ./bin/main -m "PATH_TO_MODEL" -p "Hi you how are you" -n 50 -e -ngl 33 -t 4

16
examples/main-cmake-pkg/README.md
View File

@ -17,11 +17,9 @@ In this case, CLBlast was already installed so the CMake package is referenced i
```cmd ```cmd
git clone https://github.com/ggerganov/llama.cpp git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp cd llama.cpp
mkdir build 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
cd build cmake --build build --config Release
cmake .. -DBUILD_SHARED_LIBS=OFF -DLLAMA_CLBLAST=ON -DCMAKE_PREFIX_PATH=C:/CLBlast/lib/cmake/CLBlast -G "Visual Studio 17 2022" -A x64 cmake --install build --prefix C:/LlamaCPP
cmake --build . --config Release
cmake --install . --prefix C:/LlamaCPP
``` ```
### Build main-cmake-pkg ### Build main-cmake-pkg
@ -29,9 +27,7 @@ cmake --install . --prefix C:/LlamaCPP
```cmd ```cmd
cd ..\examples\main-cmake-pkg cd ..\examples\main-cmake-pkg
mkdir build 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
cd build cmake --build build --config Release
cmake .. -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 --install build --prefix C:/MyLlamaApp
cmake --build . --config Release
cmake --install . --prefix C:/MyLlamaApp
``` ```

13
examples/server/README.md
View File

@ -74,15 +74,18 @@ page cache before using this. See https://github.com/ggerganov/llama.cpp/issues/
- Using `make`: - Using `make`:
```bash ```bash
make make server
``` ```
- Using `CMake`: - Using `CMake`:
```bash ```bash
cmake --build . --config Release cmake -B build
cmake --build build --config Release -t server
``` ```
Binary is at `./build/bin/server`
## Build with SSL ## Build with SSL
`server` can also be built with SSL support using OpenSSL 3 `server` can also be built with SSL support using OpenSSL 3
@ -99,10 +102,8 @@ page cache before using this. See https://github.com/ggerganov/llama.cpp/issues/
- Using `CMake`: - Using `CMake`:
```bash ```bash
mkdir build cmake -B build -DLLAMA_SERVER_SSL=ON
cd build cmake --build build --config Release -t server
cmake .. -DLLAMA_SERVER_SSL=ON
make server
``` ```
## Quick Start ## Quick Start