admin/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

llama.cpp verification source 2026-05-22
Some checks are pending
Copilot Setup Steps / copilot-setup-steps (push) Waiting to run
Details
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Waiting to run
Details
Python check requirements.txt / check-requirements (push) Waiting to run
Details
Python Type-Check / python type-check (push) Waiting to run
Details
Update Operations Documentation / update-ops-docs (push) Waiting to run
Details

Browse Source
This commit is contained in:
admin
2026-05-22 16:44:08 +08:00
commit 8e5a449007
2740 changed files with 1155720 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/sycl/CMakeLists.txt Normal file
View File

@@ -0,0 +1,9 @@
# MIT license
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: MIT
set(TARGET llama-ls-sycl-device)
add_executable(${TARGET} ls-sycl-device.cpp)
install(TARGETS ${TARGET} RUNTIME)
target_link_libraries(${TARGET} PRIVATE llama-common llama ${CMAKE_THREAD_LIBS_INIT})
target_compile_features(${TARGET} PRIVATE cxx_std_17)

41
examples/sycl/README.md Normal file
View File

@@ -0,0 +1,41 @@
# llama.cpp/example/sycl
This example program provides the tools for llama.cpp for SYCL on Intel GPU.
## Tool
|Tool Name| Function|Status|
|-|-|-|
|llama-ls-sycl-device| List all SYCL devices with ID, compute capability, max work group size, etc.|Support|
### llama-ls-sycl-device
List all SYCL devices with ID, compute capability, max work group size, etc.
1. Build the llama.cpp for SYCL for the specified target *(using GGML_SYCL_TARGET)*.
2. Enable oneAPI running environment *(if GGML_SYCL_TARGET is set to INTEL -default-)*
```
source /opt/intel/oneapi/setvars.sh
```
3. Execute
```
./build/bin/llama-ls-sycl-device
```
Check the ID in startup log, like:
```
found 2 SYCL devices:
| | | | |Max | |Max |Global | |
| | | | |compute|Max work|sub |mem | |
|ID| Device Type| Name|Version|units |group |group|size | Driver version|
|--|-------------------|---------------------------------------|-------|-------|--------|-----|-------|---------------------|
| 0| [level_zero:gpu:0]| Intel Arc A770 Graphics| 1.3| 512| 1024| 32| 16225M| 1.3.29138|
| 1| [level_zero:gpu:1]| Intel UHD Graphics 750| 1.3| 32| 512| 32| 62631M| 1.3.29138|
```

23
examples/sycl/build.sh Executable file
View File

@@ -0,0 +1,23 @@
#!/usr/bin/env bash
# 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 -DLLAMA_OPENSSL=OFF # faster for long-prompt inference
#for FP32
cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_OPENSSL=OFF
#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$((($(nproc)+1)/2)) -v

15
examples/sycl/ls-sycl-device.cpp Normal file
View File

@@ -0,0 +1,15 @@
//
// MIT license
// Copyright (C) 2024 Intel Corporation
// SPDX-License-Identifier: MIT
//
#include "ggml-sycl.h"
#include <clocale>
int main() {
std::setlocale(LC_NUMERIC, "C");
ggml_backend_sycl_print_sycl_devices();
return 0;
}

31
examples/sycl/run-llama2.sh Executable file
View File

@@ -0,0 +1,31 @@
#!/usr/bin/env bash
# MIT license
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: MIT
export ONEAPI_DEVICE_SELECTOR="level_zero:0"
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=99
CONTEXT=4096
#support malloc device memory more than 4GB.
export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
LOAD_MODE='--mmap'
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-completion -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 200 -e -ngl ${NGL} -s 0 -c ${CONTEXT} -mg $GGML_SYCL_DEVICE -sm none ${LOAD_MODE}
else
#use multiple GPUs with same max compute units
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-completion -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 200 -e -ngl ${NGL} -s 0 -c ${CONTEXT} ${LOAD_MODE}
fi

124
examples/sycl/start-svr.sh Executable file
View File

@@ -0,0 +1,124 @@
#!/bin/bash
# MIT license
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: MIT
Help() {
cat << EOF
Usage: $(basename "$0") [OPTIONS]
This script processes files with specified options.
Options:
-h, --help Display this help message and exit.
-c, --context <value> Set context length. Bigger need more memory.
-p, --promote <value> Prompt to start generation with.
-m, --model <value> Full model file path.
-mg,--main-gpu <value> Set main GPU ID (0 - n) for single GPU mode.
-sm,--split-mode <value> How to split the model across multiple GPUs, one of:
- none: use one GPU only
- layer (default): split layers and KV across GPUs
- row: split rows across GPUs
-ngl,--n-gpu-layers <value> Max. number of layers to store in VRAM (default: -1)
-lv,--log-verbosity <value> Set the verbosity threshold. Messages with a higher verbosity will be
ignored. Values:
- 0: generic output
- 1: error
- 2: warning
- 3: info
- 4: debug
EOF
}
BIN_FILE=./build/bin/llama-server
SEED=0
GPUS_SETTING=""
MODEL_FILE=../models/Qwen3.5-4B-Q4_0.gguf
NGL=99
CONTEXT=4096
GGML_SYCL_DEVICE=-1
SPLIT_MODE=layer
LOG_VERBOSE=3
while [[ $# -gt 0 ]]; do
case "$1" in
-c|--context)
CONTEXT=$2
# Shift twice to consume both the option flag and its value
shift
shift
;;
-m|--model)
MODEL_FILE="$2"
# Shift twice to consume both the option flag and its value
shift
shift
;;
-mg|--main-gpu)
GGML_SYCL_DEVICE=$2
SPLIT_MODE=none
# Shift twice to consume both the option flag and its value
shift
shift
;;
-sm|--split-mode)
SPLIT_MODE=$2
# Shift twice to consume both the option flag and its value
shift
shift
;;
-ngl|--n-gpu-layers)
NGL=$2
# Shift twice to consume both the option flag and its value
shift
shift
;;
-lv|--log-verbosity)
LOG_VERBOSE=$2
# Shift twice to consume both the option flag and its value
shift
shift
;;
-h|--help)
Help
exit 0
;;
*)
# Handle unknown options or stop processing options
echo "Invalid option: $1"
# Optional: exit script or shift to treat remaining as positional args
exit 1
;;
esac
done
source /opt/intel/oneapi/setvars.sh
#export GGML_SYCL_DEBUG=1
#ZES_ENABLE_SYSMAN=1, Support to get free memory of GPU by sycl::aspect::ext_intel_free_memory. Recommended to use when --split-mode = layer.
#support malloc device memory more than 4GB.
export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
echo "UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=${UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS}"
if [ $GGML_SYCL_DEVICE -ne -1 ]; then
echo "Use $GGML_SYCL_DEVICE as main GPU"
#use signle GPU only
GPUS_SETTING="-mg $GGML_SYCL_DEVICE -sm ${SPLIT_MODE}"
export ONEAPI_DEVICE_SELECTOR="level_zero:${GGML_SYCL_DEVICE}"
echo "ONEAPI_DEVICE_SELECTOR=${ONEAPI_DEVICE_SELECTOR}"
else
echo "Use all Intel GPUs, including iGPU & dGPU"
GPUS_SETTING="-sm ${SPLIT_MODE}"
fi
echo "run cmd: ZES_ENABLE_SYSMAN=1 ${BIN_FILE} -m ${MODEL_FILE} -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --mmap --host 0.0.0.0 --port 8000"
ZES_ENABLE_SYSMAN=1 ${BIN_FILE} -m ${MODEL_FILE} -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --mmap --host 0.0.0.0 --port 8000

131
examples/sycl/test.sh Executable file
View File

@@ -0,0 +1,131 @@
#!/bin/bash
# MIT license
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: MIT
Help() {
cat << EOF
Usage: $(basename "$0") [OPTIONS]
This script processes files with specified options.
Options:
-h, --help Display this help message and exit.
-c, --context <value> Set context length. Bigger need more memory.
-p, --promote <value> Prompt to start generation with.
-m, --model <value> Full model file path.
-mg,--main-gpu <value> Set main GPU ID (0 - n) for single GPU mode.
-sm,--split-mode <value> How to split the model across multiple GPUs, one of:
- none: use one GPU only
- layer (default): split layers and KV across GPUs
- row: split rows across GPUs
-ngl,--n-gpu-layers <value> Max. number of layers to store in VRAM (default: -1)
-lv,--log-verbosity <value> Set the verbosity threshold. Messages with a higher verbosity will be
ignored. Values:
- 0: generic output
- 1: error
- 2: warning
- 3: info
- 4: debug
EOF
}
BIN_FILE=./build/bin/llama-completion
SEED=0
GPUS_SETTING=""
INPUT_PROMPT="Building a website can be done in 10 simple steps:\nStep 1:"
MODEL_FILE=../models/llama-2-7b.Q4_0.gguf
NGL=99
CONTEXT=4096
GGML_SYCL_DEVICE=-1
SPLIT_MODE=layer
LOG_VERBOSE=3
while [[ $# -gt 0 ]]; do
case "$1" in
-c|--context)
CONTEXT=$2
# Shift twice to consume both the option flag and its value
shift
shift
;;
-p|--promote)
# Option that is a simple flag (boolean)
INPUT_PROMPT="$2"
# Shift once to consume the option flag
shift
shift
;;
-m|--model)
MODEL_FILE="$2"
# Shift twice to consume both the option flag and its value
shift
shift
;;
-mg|--main-gpu)
GGML_SYCL_DEVICE=$2
SPLIT_MODE=none
# Shift twice to consume both the option flag and its value
shift
shift
;;
-sm|--split-mode)
SPLIT_MODE=$2
# Shift twice to consume both the option flag and its value
shift
shift
;;
-ngl|--n-gpu-layers)
NGL=$2
# Shift twice to consume both the option flag and its value
shift
shift
;;
-lv|--log-verbosity)
LOG_VERBOSE=$2
# Shift twice to consume both the option flag and its value
shift
shift
;;
-h|--help)
Help
exit 0
;;
*)
# Handle unknown options or stop processing options
echo "Invalid option: $1"
# Optional: exit script or shift to treat remaining as positional args
exit 1
;;
esac
done
source /opt/intel/oneapi/setvars.sh
#export GGML_SYCL_DEBUG=1
#ZES_ENABLE_SYSMAN=1, Support to get free memory of GPU by sycl::aspect::ext_intel_free_memory. Recommended to use when --split-mode = layer.
#support malloc device memory more than 4GB.
export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
echo "UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=${UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS}"
if [ $GGML_SYCL_DEVICE -ne -1 ]; then
echo "Use $GGML_SYCL_DEVICE as main GPU"
#use signle GPU only
GPUS_SETTING="-mg $GGML_SYCL_DEVICE -sm ${SPLIT_MODE}"
export ONEAPI_DEVICE_SELECTOR="level_zero:${GGML_SYCL_DEVICE}"
echo "ONEAPI_DEVICE_SELECTOR=${ONEAPI_DEVICE_SELECTOR}"
else
echo "Use all Intel GPUs, including iGPU & dGPU"
GPUS_SETTING="-sm ${SPLIT_MODE}"
fi
echo "run cmd: ZES_ENABLE_SYSMAN=1 ${BIN_FILE} -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 200 -e -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --mmap "
ZES_ENABLE_SYSMAN=1 ${BIN_FILE} -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 200 -e -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --mmap

31
examples/sycl/win-build-sycl.bat Normal file
View File

@@ -0,0 +1,31 @@
:: 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" .. -DLLAMA_OPENSSL=OFF -DGGML_SYCL=ON -DCMAKE_CXX_COMPILER=icx -DBUILD_SHARED_LIBS=ON -DCMAKE_BUILD_TYPE=Release -DGGML_SYCL_F16=ON
:: for FP32
cmake -G "Ninja" .. -DLLAMA_OPENSSL=OFF -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 all binary
cmake --build . -j
if %errorlevel% neq 0 goto ERROR
cd ..
exit /B 0
:ERROR
echo comomand error: %errorlevel%
exit /B %errorlevel%

11
examples/sycl/win-run-llama2.bat Normal file
View File

@@ -0,0 +1,11 @@
:: 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
:: support malloc device memory more than 4GB.
set UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
set LOAD_MODE="--mmap"
.\build\bin\llama-completion.exe -m models\llama-2-7b.Q4_0.gguf -no-cnv -p %INPUT2% -n 400 -e -ngl 99 -s 0 %LOAD_MODE%

179
examples/sycl/win-start-svr.bat Normal file
View File

@@ -0,0 +1,179 @@
:: MIT license
:: Copyright (C) 2024 Intel Corporation
:: SPDX-License-Identifier: MIT
@echo off
setlocal EnableExtensions EnableDelayedExpansion
set "BIN_FILE=.\build\bin\llama-server.exe"
set "SEED=0"
set "GPUS_SETTING="
set "MODEL_FILE=..\models\Qwen3.5-4B-Q4_0.gguf"
set "NGL=99"
set "CONTEXT=4096"
set "GGML_SYCL_DEVICE=-1"
set "SPLIT_MODE=layer"
set "LOG_VERBOSE=3"
if "%~1"=="" goto after_args
:parse_args
if "%~1"=="" goto after_args
if /I "%~1"=="-c" (
if "%~2"=="" goto missing_value
set "CONTEXT=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--context" (
if "%~2"=="" goto missing_value
set "CONTEXT=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-m" (
if "%~2"=="" goto missing_value
set "MODEL_FILE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--model" (
if "%~2"=="" goto missing_value
set "MODEL_FILE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-mg" (
if "%~2"=="" goto missing_value
set "GGML_SYCL_DEVICE=%~2"
set "SPLIT_MODE=none"
shift
shift
goto parse_args
)
if /I "%~1"=="--main-gpu" (
if "%~2"=="" goto missing_value
set "GGML_SYCL_DEVICE=%~2"
set "SPLIT_MODE=none"
shift
shift
goto parse_args
)
if /I "%~1"=="-sm" (
if "%~2"=="" goto missing_value
set "SPLIT_MODE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--split-mode" (
if "%~2"=="" goto missing_value
set "SPLIT_MODE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-ngl" (
if "%~2"=="" goto missing_value
set "NGL=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--n-gpu-layers" (
if "%~2"=="" goto missing_value
set "NGL=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-lv" (
if "%~2"=="" goto missing_value
set "LOG_VERBOSE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--log-verbosity" (
if "%~2"=="" goto missing_value
set "LOG_VERBOSE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-h" goto help
if /I "%~1"=="--help" goto help
echo Invalid option: %~1
exit /b 1
:missing_value
echo Missing value for option: %~1
exit /b 1
:help
echo Usage: %~n0 [OPTIONS]
echo.
echo This script processes files with specified options.
echo.
echo Options:
echo -h, --help Display this help message and exit.
echo -c, --context ^<value^> Set context length. Bigger need more memory.
echo -m, --model ^<value^> Full model file path.
echo -mg,--main-gpu ^<value^> Set main GPU ID (0 - n) for single GPU mode.
echo -sm,--split-mode ^<value^> How to split the model across multiple GPUs, one of:
echo - none: use one GPU only
echo - layer (default): split layers and KV across GPUs
echo - row: split rows across GPUs
echo -ngl,--n-gpu-layers ^<value^> Max. number of layers to store in VRAM (default: -1)
echo -lv,--log-verbosity ^<value^> Set the verbosity threshold. Messages with a higher verbosity will be
echo ignored. Values:
echo - 0: generic output
echo - 1: error
echo - 2: warning
echo - 3: info
echo - 4: debug
exit /b 0
:after_args
REM In Windows CMD, source is not available; call oneAPI setvars if present.
if exist "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" (
call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" >nul
) else (
echo Warning: oneAPI setvars.bat not found. Continuing without environment setup.
)
REM Support malloc device memory more than 4GB.
set "UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1"
echo UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=%UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS%
if not "%GGML_SYCL_DEVICE%"=="-1" (
echo Use %GGML_SYCL_DEVICE% as main GPU
REM Use single GPU only.
set "GPUS_SETTING=-mg %GGML_SYCL_DEVICE% -sm %SPLIT_MODE%"
set "ONEAPI_DEVICE_SELECTOR=level_zero:%GGML_SYCL_DEVICE%"
echo ONEAPI_DEVICE_SELECTOR=%ONEAPI_DEVICE_SELECTOR%
) else (
echo Use all Intel GPUs, including iGPU ^& dGPU
set "GPUS_SETTING=-sm %SPLIT_MODE%"
)
echo run cmd: ZES_ENABLE_SYSMAN=1 %BIN_FILE% -m "%MODEL_FILE%" -ngl %NGL% -s %SEED% -c %CONTEXT% %GPUS_SETTING% -lv %LOG_VERBOSE% --mmap --host 0.0.0.0 --port 8000
set "ZES_ENABLE_SYSMAN=1"
%BIN_FILE% -m "%MODEL_FILE%" -ngl %NGL% -s %SEED% -c %CONTEXT% %GPUS_SETTING% -lv %LOG_VERBOSE% --mmap --host 0.0.0.0 --port 8000
endlocal

201
examples/sycl/win-test.bat Normal file
View File

@@ -0,0 +1,201 @@
:: MIT license
:: Copyright (C) 2024 Intel Corporation
:: SPDX-License-Identifier: MIT
@echo off
setlocal EnableExtensions EnableDelayedExpansion
REM MIT license
REM Copyright (C) 2024 Intel Corporation
REM SPDX-License-Identifier: MIT
set "BIN_FILE=.\build\bin\llama-completion.exe"
set "SEED=0"
set "GPUS_SETTING="
set "INPUT_PROMPT=Building a website can be done in 10 simple steps:^nStep 1:"
set "MODEL_FILE=..\models\llama-2-7b.Q4_0.gguf"
set "NGL=99"
set "CONTEXT=4096"
set "GGML_SYCL_DEVICE=-1"
set "SPLIT_MODE=layer"
set "LOG_VERBOSE=3"
if "%~1"=="" goto after_args
:parse_args
if "%~1"=="" goto after_args
if /I "%~1"=="-c" (
if "%~2"=="" goto missing_value
set "CONTEXT=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--context" (
if "%~2"=="" goto missing_value
set "CONTEXT=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-p" (
if "%~2"=="" goto missing_value
set "INPUT_PROMPT=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--promote" (
if "%~2"=="" goto missing_value
set "INPUT_PROMPT=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-m" (
if "%~2"=="" goto missing_value
set "MODEL_FILE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--model" (
if "%~2"=="" goto missing_value
set "MODEL_FILE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-mg" (
if "%~2"=="" goto missing_value
set "GGML_SYCL_DEVICE=%~2"
set "SPLIT_MODE=none"
shift
shift
goto parse_args
)
if /I "%~1"=="--main-gpu" (
if "%~2"=="" goto missing_value
set "GGML_SYCL_DEVICE=%~2"
set "SPLIT_MODE=none"
shift
shift
goto parse_args
)
if /I "%~1"=="-sm" (
if "%~2"=="" goto missing_value
set "SPLIT_MODE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--split-mode" (
if "%~2"=="" goto missing_value
set "SPLIT_MODE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-ngl" (
if "%~2"=="" goto missing_value
set "NGL=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--n-gpu-layers" (
if "%~2"=="" goto missing_value
set "NGL=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-lv" (
if "%~2"=="" goto missing_value
set "LOG_VERBOSE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--log-verbosity" (
if "%~2"=="" goto missing_value
set "LOG_VERBOSE=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-h" goto help
if /I "%~1"=="--help" goto help
echo Invalid option: %~1
exit /b 1
:missing_value
echo Missing value for option: %~1
exit /b 1
:help
echo Usage: %~n0 [OPTIONS]
echo.
echo This script processes files with specified options.
echo.
echo Options:
echo -h, --help Display this help message and exit.
echo -c, --context ^<value^> Set context length. Bigger need more memory.
echo -p, --promote ^<value^> Prompt to start generation with.
echo -m, --model ^<value^> Full model file path.
echo -mg,--main-gpu ^<value^> Set main GPU ID (0 - n) for single GPU mode.
echo -sm,--split-mode ^<value^> How to split the model across multiple GPUs, one of:
echo - none: use one GPU only
echo - layer (default): split layers and KV across GPUs
echo - row: split rows across GPUs
echo -ngl,--n-gpu-layers ^<value^> Max. number of layers to store in VRAM (default: -1)
echo -lv,--log-verbosity ^<value^> Set the verbosity threshold. Messages with a higher verbosity will be
echo ignored. Values:
echo - 0: generic output
echo - 1: error
echo - 2: warning
echo - 3: info
echo - 4: debug
exit /b 0
:after_args
REM In Windows CMD, source is not available; call oneAPI setvars if present.
if exist "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" (
call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" >nul
) else (
echo Warning: oneAPI setvars.bat not found. Continuing without environment setup.
)
REM Support malloc device memory more than 4GB.
set "UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1"
echo UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=%UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS%
if not "%GGML_SYCL_DEVICE%"=="-1" (
echo Use %GGML_SYCL_DEVICE% as main GPU
REM Use single GPU only.
set "GPUS_SETTING=-mg %GGML_SYCL_DEVICE% -sm %SPLIT_MODE%"
set "ONEAPI_DEVICE_SELECTOR=level_zero:%GGML_SYCL_DEVICE%"
echo ONEAPI_DEVICE_SELECTOR=%ONEAPI_DEVICE_SELECTOR%
) else (
echo Use all Intel GPUs, including iGPU ^& dGPU
set "GPUS_SETTING=-sm %SPLIT_MODE%"
)
echo run cmd: ZES_ENABLE_SYSMAN=1 %BIN_FILE% -m %MODEL_FILE% -no-cnv -p "%INPUT_PROMPT%" -n 200 -e -ngl %NGL% -s %SEED% -c %CONTEXT% %GPUS_SETTING% -lv %LOG_VERBOSE% --mmap
set "ZES_ENABLE_SYSMAN=1"
%BIN_FILE% -m "%MODEL_FILE%" -no-cnv -p "%INPUT_PROMPT%" -n 200 -e -ngl %NGL% -s %SEED% -c %CONTEXT% %GPUS_SETTING% -lv %LOG_VERBOSE% --mmap
endlocal