ggml : add unified SYCL backend for Intel GPUs (#2690)
* first update for migration * update init_cublas * add debug functio, commit all help code * step 1 * step 2 * step3 add fp16, slower 31->28 * add GGML_LIST_DEVICE function * step 5 format device and print * step6, enhance error check, remove CUDA macro, enhance device id to fix none-zero id issue * support main device is non-zero * step7 add debug for code path, rm log * step 8, rename all macro & func from cuda by sycl * fix error of select non-zero device, format device list * ren ggml-sycl.hpp -> ggml-sycl.h * clear CMAKE to rm unused lib and options * correct queue: rm dtct:get_queue * add print tensor function to debug * fix error: wrong result in 658746bb26702e50f2c59c0e4ada8e9da6010481 * summary dpct definition in one header file to replace folder:dpct * refactor device log * mv dpct definition from folder dpct to ggml-sycl.h * update readme, refactor build script * fix build with sycl * set nthread=1 when sycl, increase performance * add run script, comment debug code * add ls-sycl-device tool * add ls-sycl-device, rm unused files * rm rear space * dos2unix * Update README_sycl.md * fix return type * remove sycl version from include path * restore rm code to fix hang issue * add syc and link for sycl readme * rm original sycl code before refactor * fix code err * add know issue for pvc hang issue * enable SYCL_F16 support * align pr4766 * check for sycl blas, better performance * cleanup 1 * remove extra endif * add build&run script, clean CMakefile, update guide by review comments * rename macro to intel hardware * editor config format * format fixes * format fixes * editor format fix * Remove unused headers * skip build sycl tool for other code path * replace tab by space * fix blas matmul function * fix mac build * restore hip dependency * fix conflict * ren as review comments * mv internal function to .cpp file * export funciton print_sycl_devices(), mv class dpct definition to source file * update CI/action for sycl code, fix CI error of repeat/dup * fix action ID format issue * rm unused strategy * enable llama_f16 in ci * fix conflict * fix build break on MacOS, due to CI of MacOS depend on external ggml, instead of internal ggml * fix ci cases for unsupported data type * revert unrelated changed in cuda cmake remove useless nommq fix typo of GGML_USE_CLBLAS_SYCL * revert hip cmake changes * fix indent * add prefix in func name * revert no mmq * rm cpu blas duplicate * fix no_new_line * fix src1->type==F16 bug. * pass batch offset for F16 src1 * fix batch error * fix wrong code * revert sycl checking in test-sampling * pass void as arguments of ggml_backend_sycl_print_sycl_devices * remove extra blank line in test-sampling * revert setting n_threads in sycl * implement std::isinf for icpx with fast math. * Update ci/run.sh Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update examples/sycl/run-llama2.sh Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update examples/sycl/run-llama2.sh Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update CMakeLists.txt Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update CMakeLists.txt Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update CMakeLists.txt Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update CMakeLists.txt Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * add copyright and MIT license declare * update the cmd example --------- Co-authored-by: jianyuzh <jianyu.zhang@intel.com> Co-authored-by: luoyu-intel <yu.luo@intel.com> Co-authored-by: Meng, Hengyu <hengyu.meng@intel.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Abhilash Majumder
GitHub
parent
b764b8f1d0
commit
0f648573dd
22 changed files with 15764 additions and 24 deletions
|
|
@ -23,6 +23,9 @@ else()
|
|||
add_subdirectory(infill)
|
||||
add_subdirectory(llama-bench)
|
||||
add_subdirectory(llava)
|
||||
if (LLAMA_SYCL)
|
||||
add_subdirectory(sycl)
|
||||
endif()
|
||||
add_subdirectory(main)
|
||||
add_subdirectory(tokenize)
|
||||
add_subdirectory(parallel)
|
||||
|
|
|
|||
|
|
@ -2099,7 +2099,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
|
|||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
#if defined(GGML_USE_CUBLAS) || defined(GGML_USE_SYCL)
|
||||
std::string arg_next = argv[i];
|
||||
|
||||
// split string by , and /
|
||||
|
|
@ -2125,7 +2125,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
|
|||
}
|
||||
else if (arg == "--no-mul-mat-q" || arg == "-nommq")
|
||||
{
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
#if defined(GGML_USE_CUBLAS) || defined(GGML_USE_SYCL)
|
||||
params.mul_mat_q = false;
|
||||
#else
|
||||
LOG_WARNING("warning: llama.cpp was compiled without cuBLAS. Disabling mul_mat_q kernels has no effect.\n", {});
|
||||
|
|
@ -2138,7 +2138,7 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
|
|||
invalid_param = true;
|
||||
break;
|
||||
}
|
||||
#ifdef GGML_USE_CUBLAS
|
||||
#if defined(GGML_USE_CUBLAS) || defined(GGML_USE_SYCL)
|
||||
params.main_gpu = std::stoi(argv[i]);
|
||||
#else
|
||||
LOG_WARNING("llama.cpp was compiled without cuBLAS. It is not possible to set a main GPU.", {});
|
||||
|
|
|
|||
9
examples/sycl/CMakeLists.txt
Normal file
9
examples/sycl/CMakeLists.txt
Normal file
|
|
@ -0,0 +1,9 @@
|
|||
# MIT license
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: MIT
|
||||
|
||||
set(TARGET ls-sycl-device)
|
||||
add_executable(${TARGET} ls-sycl-device.cpp)
|
||||
install(TARGETS ${TARGET} RUNTIME)
|
||||
target_link_libraries(${TARGET} PRIVATE common llama ${CMAKE_THREAD_LIBS_INIT})
|
||||
target_compile_features(${TARGET} PRIVATE cxx_std_17)
|
||||
47
examples/sycl/README.md
Normal file
47
examples/sycl/README.md
Normal file
|
|
@ -0,0 +1,47 @@
|
|||
# llama.cpp/example/sycl
|
||||
|
||||
This example program provide the tools for llama.cpp for SYCL on Intel GPU.
|
||||
|
||||
## Tool
|
||||
|
||||
|Tool Name| Function|Status|
|
||||
|-|-|-|
|
||||
|ls-sycl-device| List all SYCL devices with ID, compute capability, max work group size, ect.|Support|
|
||||
|
||||
### ls-sycl-device
|
||||
|
||||
List all SYCL devices with ID, compute capability, max work group size, ect.
|
||||
|
||||
1. Build the llama.cpp for SYCL for all targets.
|
||||
|
||||
2. Enable oneAPI running environment
|
||||
|
||||
```
|
||||
source /opt/intel/oneapi/setvars.sh
|
||||
```
|
||||
|
||||
3. Execute
|
||||
|
||||
```
|
||||
./build/bin/ls-sycl-device
|
||||
```
|
||||
|
||||
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|
|
||||
20
examples/sycl/build.sh
Executable file
20
examples/sycl/build.sh
Executable file
|
|
@ -0,0 +1,20 @@
|
|||
|
||||
# MIT license
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: MIT
|
||||
|
||||
mkdir -p build
|
||||
cd build
|
||||
source /opt/intel/oneapi/setvars.sh
|
||||
|
||||
#for FP16
|
||||
#cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON # faster for long-prompt inference
|
||||
|
||||
#for FP32
|
||||
cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
|
||||
|
||||
#build example/main only
|
||||
#cmake --build . --config Release --target main
|
||||
|
||||
#build all binary
|
||||
cmake --build . --config Release -v
|
||||
11
examples/sycl/ls-sycl-device.cpp
Normal file
11
examples/sycl/ls-sycl-device.cpp
Normal file
|
|
@ -0,0 +1,11 @@
|
|||
/*MIT license
|
||||
Copyright (C) 2024 Intel Corporation
|
||||
SPDX-License-Identifier: MIT
|
||||
*/
|
||||
|
||||
#include "ggml-sycl.h"
|
||||
|
||||
int main(int argc, char ** argv) {
|
||||
ggml_backend_sycl_print_sycl_devices();
|
||||
return 0;
|
||||
}
|
||||
19
examples/sycl/run-llama2.sh
Executable file
19
examples/sycl/run-llama2.sh
Executable file
|
|
@ -0,0 +1,19 @@
|
|||
#!/bin/bash
|
||||
|
||||
# MIT license
|
||||
# Copyright (C) 2024 Intel Corporation
|
||||
# SPDX-License-Identifier: MIT
|
||||
|
||||
INPUT2="Building a website can be done in 10 simple steps:\nStep 1:"
|
||||
source /opt/intel/oneapi/setvars.sh
|
||||
|
||||
if [ $# -gt 0 ]; then
|
||||
export GGML_SYCL_DEVICE=$1
|
||||
else
|
||||
export GGML_SYCL_DEVICE=0
|
||||
fi
|
||||
echo GGML_SYCL_DEVICE=$GGML_SYCL_DEVICE
|
||||
#export GGML_SYCL_DEBUG=1
|
||||
./build/bin/main -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0
|
||||
#./build/bin/main -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 5 -e -ngl 33 -t 1 -s 0
|
||||
|
||||
Loading…
Add table
Add a link
Reference in a new issue