Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

cleanup, try to add version tagging

Browse Source
This commit is contained in:
Concedo
2024-11-23 12:59:06 +08:00
parent 1dd37933e3
commit afc575fbd8
141 changed files with 123 additions and 14439 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/sycl/build.sh
-23
View File
@@ -1,23 +0,0 @@
# 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 .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON # faster for long-prompt inference
#for FP32
cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
#build example/main
#cmake --build . --config Release --target main
#build example/llama-bench
#cmake --build . --config Release --target llama-bench
#build all binary
cmake --build . --config Release -j -v
examples/sycl/ls-sycl-device.cpp
-13
View File
@@ -1,13 +0,0 @@
//
// MIT license
// Copyright (C) 2024 Intel Corporation
// SPDX-License-Identifier: MIT
//
#include "ggml-sycl.h"
int main() {
ggml_backend_sycl_print_sycl_devices();
return 0;
}
examples/sycl/run-llama2.sh
-27
View File
@@ -1,27 +0,0 @@
#!/bin/bash
# MIT license
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: MIT
source /opt/intel/oneapi/setvars.sh
#export GGML_SYCL_DEBUG=1
#ZES_ENABLE_SYSMAN=1, Support to get free memory of GPU by sycl::aspect::ext_intel_free_memory. Recommended to use when --split-mode = layer.
INPUT_PROMPT="Building a website can be done in 10 simple steps:\nStep 1:"
MODEL_FILE=models/llama-2-7b.Q4_0.gguf
NGL=33
CONEXT=8192
if [ $# -gt 0 ]; then
GGML_SYCL_DEVICE=$1
echo "use $GGML_SYCL_DEVICE as main GPU"
#use signle GPU only
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONEXT} -mg $GGML_SYCL_DEVICE -sm none
else
#use multiple GPUs with same max compute units
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONEXT}
fi
examples/sycl/win-build-sycl.bat
-33
View File
@@ -1,33 +0,0 @@
:: MIT license
:: Copyright (C) 2024 Intel Corporation
:: SPDX-License-Identifier: MIT
IF not exist build (mkdir build)
cd build
if %errorlevel% neq 0 goto ERROR
@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
if %errorlevel% neq 0 goto ERROR
:: for FP16
:: faster for long-prompt inference
:: cmake -G "MinGW Makefiles" .. -DGGML_SYCL=ON -DCMAKE_CXX_COMPILER=icx -DBUILD_SHARED_LIBS=ON -DCMAKE_BUILD_TYPE=Release -DGGML_SYCL_F16=ON
:: for FP32
cmake -G "Ninja" .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx -DBUILD_SHARED_LIBS=ON -DCMAKE_BUILD_TYPE=Release
if %errorlevel% neq 0 goto ERROR
:: build example/main only
:: make main
:: build all binary
cmake --build . -j
if %errorlevel% neq 0 goto ERROR
cd ..
exit /B 0
:ERROR
echo comomand error: %errorlevel%
exit /B %errorlevel%
examples/sycl/win-run-llama2.bat
-9
View File
@@ -1,9 +0,0 @@
:: MIT license
:: Copyright (C) 2024 Intel Corporation
:: SPDX-License-Identifier: MIT
set INPUT2="Building a website can be done in 10 simple steps:\nStep 1:"
@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
.\build\bin\llama-cli.exe -m models\llama-2-7b.Q4_0.gguf -p %INPUT2% -n 400 -e -ngl 33 -s 0