mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-11 13:30:35 +00:00
support SYCL backend windows build (#5208)
* support SYCL backend windows build * add windows build in CI * add for win build CI * correct install oneMKL * fix install issue * fix ci * fix install cmd * fix install cmd * fix install cmd * fix install cmd * fix install cmd * fix win build * fix win build * fix win build * restore other CI part * restore as base * rm no new line * fix no new line issue, add -j * fix grammer issue * allow to trigger manually, fix format issue * fix format * add newline * fix format * fix format * fix format issuse --------- Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
This commit is contained in:
Neo Zhang Jianyu
GitHub
parent
e8dc55d006
commit
01684139c3
25
.github/workflows/build.yml
vendored
25
.github/workflows/build.yml
vendored
@ -565,6 +565,31 @@ jobs:
|
||||
path: |
|
||||
cudart-llama-bin-win-cu${{ matrix.cuda }}-x64.zip
|
||||
|
||||
windows-latest-cmake-sycl:
|
||||
runs-on: windows-latest
|
||||
defaults:
|
||||
run:
|
||||
shell: bash
|
||||
|
||||
env:
|
||||
WINDOWS_BASEKIT_URL: https://registrationcenter-download.intel.com/akdlm/IRC_NAS/62641e01-1e8d-4ace-91d6-ae03f7f8a71f/w_BaseKit_p_2024.0.0.49563_offline.exe
|
||||
WINDOWS_DPCPP_MKL: intel.oneapi.win.cpp-dpcpp-common:intel.oneapi.win.mkl.devel
|
||||
|
||||
|
||||
steps:
|
||||
- name: Clone
|
||||
id: checkout
|
||||
uses: actions/checkout@v3
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Install
|
||||
run: scripts/install-oneapi.bat $WINDOWS_BASEKIT_URL $WINDOWS_DPCPP_MKL
|
||||
|
||||
- name: Build
|
||||
id: cmake_build
|
||||
run: examples/sycl/win-build-sycl.bat
|
||||
|
||||
ios-xcode-build:
|
||||
runs-on: macos-latest
|
||||
|
||||
|
||||
6
.github/workflows/editorconfig.yml
vendored
6
.github/workflows/editorconfig.yml
vendored
@ -1,6 +1,12 @@
|
||||
name: EditorConfig Checker
|
||||
|
||||
on:
|
||||
workflow_dispatch: # allows manual triggering
|
||||
inputs:
|
||||
create_release:
|
||||
description: 'Create new release'
|
||||
required: true
|
||||
type: boolean
|
||||
push:
|
||||
branches:
|
||||
- master
|
||||
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@ -89,3 +89,4 @@ examples/jeopardy/results.txt
|
||||
|
||||
poetry.lock
|
||||
poetry.toml
|
||||
nppBackup
|
||||
|
||||
@ -507,7 +507,11 @@ if (LLAMA_SYCL)
|
||||
set(GGML_HEADERS_SYCL ggml.h ggml-sycl.h)
|
||||
set(GGML_SOURCES_SYCL ggml-sycl.cpp)
|
||||
|
||||
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} sycl OpenCL mkl_core pthread m dl mkl_sycl_blas mkl_intel_ilp64 mkl_tbb_thread)
|
||||
if (WIN32)
|
||||
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} -fsycl sycl7 OpenCL mkl_sycl_blas_dll.lib mkl_intel_ilp64_dll.lib mkl_sequential_dll.lib mkl_core_dll.lib)
|
||||
else()
|
||||
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} -fsycl OpenCL mkl_core pthread m dl mkl_sycl_blas mkl_intel_ilp64 mkl_tbb_thread)
|
||||
endif()
|
||||
endif()
|
||||
|
||||
if (LLAMA_KOMPUTE)
|
||||
|
||||
@ -8,10 +8,14 @@
|
||||
|
||||
[Linux](#linux)
|
||||
|
||||
[Windows](#windows)
|
||||
|
||||
[Environment Variable](#environment-variable)
|
||||
|
||||
[Known Issue](#known-issue)
|
||||
|
||||
[Q&A](#q&a)
|
||||
|
||||
[Todo](#todo)
|
||||
|
||||
## Background
|
||||
@ -33,7 +37,7 @@ For Intel CPU, recommend to use llama.cpp for X86 (Intel MKL building).
|
||||
|OS|Status|Verified|
|
||||
|-|-|-|
|
||||
|Linux|Support|Ubuntu 22.04|
|
||||
|Windows|Ongoing| |
|
||||
|Windows|Support|Windows 11|
|
||||
|
||||
|
||||
## Intel GPU
|
||||
@ -42,7 +46,7 @@ For Intel CPU, recommend to use llama.cpp for X86 (Intel MKL building).
|
||||
|-|-|-|
|
||||
|Intel Data Center Max Series| Support| Max 1550|
|
||||
|Intel Data Center Flex Series| Support| Flex 170|
|
||||
|Intel Arc Series| Support| Arc 770|
|
||||
|Intel Arc Series| Support| Arc 770, 730M|
|
||||
|Intel built-in Arc GPU| Support| built-in Arc GPU in Meteor Lake|
|
||||
|Intel iGPU| Support| iGPU in i5-1250P, i7-1165G7|
|
||||
|
||||
@ -131,6 +135,7 @@ cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
|
||||
#build all binary
|
||||
cmake --build . --config Release -v
|
||||
|
||||
cd ..
|
||||
```
|
||||
|
||||
or
|
||||
@ -195,7 +200,7 @@ GGML_SYCL_DEVICE=0 ./build/bin/main -m models/llama-2-7b.Q4_0.gguf -p "Building
|
||||
or run by script:
|
||||
|
||||
```
|
||||
./examples/sycl/run_llama2.sh
|
||||
./examples/sycl/run-llama2.sh
|
||||
```
|
||||
|
||||
Note:
|
||||
@ -205,11 +210,175 @@ Note:
|
||||
|
||||
5. Check the device ID in output
|
||||
|
||||
Like：
|
||||
Like:
|
||||
```
|
||||
Using device **0** (Intel(R) Arc(TM) A770 Graphics) as main device
|
||||
```
|
||||
|
||||
## Windows
|
||||
|
||||
### Setup Environment
|
||||
|
||||
1. Install Intel GPU driver.
|
||||
|
||||
Please install Intel GPU driver by official guide: [Install GPU Drivers](https://www.intel.com/content/www/us/en/products/docs/discrete-gpus/arc/software/drivers.html).
|
||||
|
||||
2. Install Intel® oneAPI Base toolkit.
|
||||
|
||||
a. Please follow the procedure in [Get the Intel® oneAPI Base Toolkit ](https://www.intel.com/content/www/us/en/developer/tools/oneapi/base-toolkit.html).
|
||||
|
||||
Recommend to install to default folder: **/opt/intel/oneapi**.
|
||||
|
||||
Following guide uses the default folder as example. If you use other folder, please modify the following guide info with your folder.
|
||||
|
||||
b. Enable oneAPI running environment:
|
||||
|
||||
- In Search, input 'oneAPI'.
|
||||
|
||||
Search & open "Intel oneAPI command prompt for Intel 64 for Visual Studio 2022"
|
||||
|
||||
- In Run:
|
||||
|
||||
In CMD:
|
||||
```
|
||||
"C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64
|
||||
```
|
||||
|
||||
c. Check GPU
|
||||
|
||||
In oneAPI command line:
|
||||
|
||||
```
|
||||
sycl-ls
|
||||
```
|
||||
|
||||
There should be one or more level-zero devices. Like **[ext_oneapi_level_zero:gpu:0]**.
|
||||
|
||||
Output (example):
|
||||
```
|
||||
[opencl:acc:0] Intel(R) FPGA Emulation Platform for OpenCL(TM), Intel(R) FPGA Emulation Device OpenCL 1.2 [2023.16.10.0.17_160000]
|
||||
[opencl:cpu:1] Intel(R) OpenCL, 11th Gen Intel(R) Core(TM) i7-1185G7 @ 3.00GHz OpenCL 3.0 (Build 0) [2023.16.10.0.17_160000]
|
||||
[opencl:gpu:2] Intel(R) OpenCL Graphics, Intel(R) Iris(R) Xe Graphics OpenCL 3.0 NEO [31.0.101.5186]
|
||||
[ext_oneapi_level_zero:gpu:0] Intel(R) Level-Zero, Intel(R) Iris(R) Xe Graphics 1.3 [1.3.28044]
|
||||
|
||||
```
|
||||
|
||||
3. Install cmake & make
|
||||
|
||||
a. Download & install cmake for windows: https://cmake.org/download/
|
||||
|
||||
b. Download & install make for windows provided by mingw-w64: https://www.mingw-w64.org/downloads/
|
||||
|
||||
|
||||
### Build locally:
|
||||
|
||||
In oneAPI command line window:
|
||||
|
||||
```
|
||||
mkdir -p build
|
||||
cd build
|
||||
@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
|
||||
|
||||
:: for FP16
|
||||
:: faster for long-prompt inference
|
||||
:: cmake -G "MinGW Makefiles" .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release -DLLAMA_SYCL_F16=ON
|
||||
|
||||
:: for FP32
|
||||
cmake -G "MinGW Makefiles" .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release
|
||||
|
||||
|
||||
:: build example/main only
|
||||
:: make main
|
||||
|
||||
:: build all binary
|
||||
make -j
|
||||
cd ..
|
||||
```
|
||||
|
||||
or
|
||||
|
||||
```
|
||||
.\examples\sycl\win-build-sycl.bat
|
||||
```
|
||||
|
||||
Note:
|
||||
|
||||
- By default, it will build for all binary files. It will take more time. To reduce the time, we recommend to build for **example/main** only.
|
||||
|
||||
### Run
|
||||
|
||||
1. Put model file to folder **models**
|
||||
|
||||
2. Enable oneAPI running environment
|
||||
|
||||
- In Search, input 'oneAPI'.
|
||||
|
||||
Search & open "Intel oneAPI command prompt for Intel 64 for Visual Studio 2022"
|
||||
|
||||
- In Run:
|
||||
|
||||
In CMD:
|
||||
```
|
||||
"C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64
|
||||
```
|
||||
|
||||
3. List device ID
|
||||
|
||||
Run without parameter:
|
||||
|
||||
```
|
||||
build\bin\ls-sycl-device.exe
|
||||
|
||||
or
|
||||
|
||||
build\bin\main.exe
|
||||
```
|
||||
|
||||
Check the ID in startup log, like:
|
||||
|
||||
```
|
||||
found 4 SYCL devices:
|
||||
Device 0: Intel(R) Arc(TM) A770 Graphics, compute capability 1.3,
|
||||
max compute_units 512, max work group size 1024, max sub group size 32, global mem size 16225243136
|
||||
Device 1: Intel(R) FPGA Emulation Device, compute capability 1.2,
|
||||
max compute_units 24, max work group size 67108864, max sub group size 64, global mem size 67065057280
|
||||
Device 2: 13th Gen Intel(R) Core(TM) i7-13700K, compute capability 3.0,
|
||||
max compute_units 24, max work group size 8192, max sub group size 64, global mem size 67065057280
|
||||
Device 3: Intel(R) Arc(TM) A770 Graphics, compute capability 3.0,
|
||||
max compute_units 512, max work group size 1024, max sub group size 32, global mem size 16225243136
|
||||
|
||||
```
|
||||
|
||||
|Attribute|Note|
|
||||
|-|-|
|
||||
|compute capability 1.3|Level-zero running time, recommended |
|
||||
|compute capability 3.0|OpenCL running time, slower than level-zero in most cases|
|
||||
|
||||
4. Set device ID and execute llama.cpp
|
||||
|
||||
Set device ID = 0 by **set GGML_SYCL_DEVICE=0**
|
||||
|
||||
```
|
||||
set GGML_SYCL_DEVICE=0
|
||||
build\bin\main.exe -m models\llama-2-7b.Q4_0.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 400 -e -ngl 33 -s 0
|
||||
```
|
||||
or run by script:
|
||||
|
||||
```
|
||||
.\examples\sycl\win-run-llama2.bat
|
||||
```
|
||||
|
||||
Note:
|
||||
|
||||
- By default, mmap is used to read model file. In some cases, it leads to the hang issue. Recommend to use parameter **--no-mmap** to disable mmap() to skip this issue.
|
||||
|
||||
|
||||
5. Check the device ID in output
|
||||
|
||||
Like:
|
||||
```
|
||||
Using device **0** (Intel(R) Arc(TM) A770 Graphics) as main device
|
||||
```
|
||||
|
||||
## Environment Variable
|
||||
|
||||
@ -220,7 +389,7 @@ Using device **0** (Intel(R) Arc(TM) A770 Graphics) as main device
|
||||
|LLAMA_SYCL|ON (mandatory)|Enable build with SYCL code path. <br>For FP32/FP16, LLAMA_SYCL=ON is mandatory.|
|
||||
|LLAMA_SYCL_F16|ON (optional)|Enable FP16 build with SYCL code path. Faster for long-prompt inference. <br>For FP32, not set it.|
|
||||
|CMAKE_C_COMPILER|icx|Use icx compiler for SYCL code path|
|
||||
|CMAKE_CXX_COMPILER|icpx|use icpx for SYCL code path|
|
||||
|CMAKE_CXX_COMPILER|icpx (Linux), icx (Windows)|use icpx/icx for SYCL code path|
|
||||
|
||||
#### Running
|
||||
|
||||
@ -232,19 +401,24 @@ Using device **0** (Intel(R) Arc(TM) A770 Graphics) as main device
|
||||
|
||||
## Known Issue
|
||||
|
||||
- Error: `error while loading shared libraries: libsycl.so.7: cannot open shared object file: No such file or directory`.
|
||||
|
||||
Miss to enable oneAPI running environment.
|
||||
|
||||
Install oneAPI base toolkit and enable it by: `source /opt/intel/oneapi/setvars.sh`.
|
||||
|
||||
|
||||
- Hang during startup
|
||||
|
||||
llama.cpp use mmap as default way to read model file and copy to GPU. In some system, memcpy will be abnormal and block.
|
||||
|
||||
Solution: add **--no-mmap**.
|
||||
|
||||
## Q&A
|
||||
|
||||
- Error: `error while loading shared libraries: libsycl.so.7: cannot open shared object file: No such file or directory`.
|
||||
|
||||
Miss to enable oneAPI running environment.
|
||||
|
||||
Install oneAPI base toolkit and enable it by: `source /opt/intel/oneapi/setvars.sh`.
|
||||
|
||||
- In Windows, no result, not error.
|
||||
|
||||
Miss to enable oneAPI running environment.
|
||||
|
||||
## Todo
|
||||
|
||||
- Support to build in Windows.
|
||||
@ -10,6 +10,8 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++
|
||||
|
||||
### Hot topics
|
||||
|
||||
- ⚠️ Incoming backends: https://github.com/ggerganov/llama.cpp/discussions/5138
|
||||
- [SYCL backend](README-sycl.md) is ready (1/28/2024), support Linux/Windows in Intel GPUs (iGPU, Arc/Flex/Max series)
|
||||
- New SOTA quantized models, including pure 2-bits: https://huggingface.co/ikawrakow
|
||||
- Collecting Apple Silicon performance stats:
|
||||
- M-series: https://github.com/ggerganov/llama.cpp/discussions/4167
|
||||
@ -604,7 +606,7 @@ Building the program with BLAS support may lead to some performance improvements
|
||||
|
||||
llama.cpp based on SYCL is used to support Intel GPU (Data Center Max series, Flex series, Arc series, Built-in GPU and iGPU).
|
||||
|
||||
For detailed info, please refer to [llama.cpp for SYCL](README_sycl.md).
|
||||
For detailed info, please refer to [llama.cpp for SYCL](README-sycl.md).
|
||||
|
||||
|
||||
### Prepare Data & Run
|
||||
|
||||
23
examples/sycl/win-build-sycl.bat
Normal file
23
examples/sycl/win-build-sycl.bat
Normal file
@ -0,0 +1,23 @@
|
||||
|
||||
:: MIT license
|
||||
:: Copyright (C) 2024 Intel Corporation
|
||||
:: SPDX-License-Identifier: MIT
|
||||
|
||||
mkdir -p build
|
||||
cd build
|
||||
@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
|
||||
|
||||
:: for FP16
|
||||
:: faster for long-prompt inference
|
||||
:: cmake -G "MinGW Makefiles" .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release -DLLAMA_SYCL_F16=ON
|
||||
|
||||
:: for FP32
|
||||
cmake -G "MinGW Makefiles" .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release
|
||||
|
||||
|
||||
:: build example/main only
|
||||
:: make main
|
||||
|
||||
:: build all binary
|
||||
make -j
|
||||
cd ..
|
||||
13
examples/sycl/win-run-llama2.bat
Normal file
13
examples/sycl/win-run-llama2.bat
Normal file
@ -0,0 +1,13 @@
|
||||
:: MIT license
|
||||
:: Copyright (C) 2024 Intel Corporation
|
||||
:: SPDX-License-Identifier: MIT
|
||||
|
||||
INPUT2="Building a website can be done in 10 simple steps:\nStep 1:"
|
||||
@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
|
||||
|
||||
|
||||
set GGML_SYCL_DEVICE=0
|
||||
rem set GGML_SYCL_DEBUG=1
|
||||
.\build\bin\main.exe -m models\llama-2-7b.Q4_0.gguf -p %INPUT2% -n 400 -e -ngl 33 -s 0
|
||||
|
||||
|
||||
19
scripts/install-oneapi.bat
Normal file
19
scripts/install-oneapi.bat
Normal file
@ -0,0 +1,19 @@
|
||||
:: MIT license
|
||||
:: Copyright (C) 2024 Intel Corporation
|
||||
:: SPDX-License-Identifier: MIT
|
||||
|
||||
|
||||
set URL=%1
|
||||
set COMPONENTS=%2
|
||||
|
||||
curl.exe --output %TEMP%\webimage.exe --url %URL% --retry 5 --retry-delay 5
|
||||
start /b /wait %TEMP%\webimage.exe -s -x -f webimage_extracted --log extract.log
|
||||
del %TEMP%\webimage.exe
|
||||
if "%COMPONENTS%"=="" (
|
||||
webimage_extracted\bootstrapper.exe -s --action install --eula=accept -p=NEED_VS2017_INTEGRATION=0 -p=NEED_VS2019_INTEGRATION=0 -p=NEED_VS2022_INTEGRATION=0 --log-dir=.
|
||||
) else (
|
||||
webimage_extracted\bootstrapper.exe -s --action install --components=%COMPONENTS% --eula=accept -p=NEED_VS2017_INTEGRATION=0 -p=NEED_VS2019_INTEGRATION=0 -p=NEED_VS2022_INTEGRATION=0 --log-dir=.
|
||||
)
|
||||
set installer_exit_code=%ERRORLEVEL%
|
||||
rd /s/q "webimage_extracted"
|
||||
exit /b %installer_exit_code%
|
||||
Loading…
Reference in New Issue
Block a user