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

sycl : update guide Q&A and script for device setting (#26442)

Browse Source
This commit is contained in:
Neo Zhang
2026-08-07 08:18:47 +03:00
committed by GitHub
parent eef5f3e343
commit c1f4109898
5 changed files with 115 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/sycl/start-svr.sh
+14 -7
View File
@@ -12,6 +12,7 @@ This script processes files with specified options.
Options:
-h, --help Display this help message and exit.
-d, --device <value> Set SYCL devices (default: SYCL0).
-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.
@@ -41,10 +42,16 @@ MODEL_FILE=../models/Qwen3.5-4B-Q4_0.gguf
NGL=99
CONTEXT=4096
GGML_SYCL_DEVICE=-1
SYCL_DEVICES="SYCL0"
SPLIT_MODE=layer
LOG_VERBOSE=3
while [[ $# -gt 0 ]]; do
case "$1" in
-d|--device)
SYCL_DEVICES="$2"
shift
shift
;;
-c|--context)
CONTEXT=$2
# Shift twice to consume both the option flag and its value
@@ -95,8 +102,6 @@ while [[ $# -gt 0 ]]; do
esac
done
source /opt/intel/oneapi/setvars.sh
#export GGML_SYCL_DEBUG=1
@@ -107,17 +112,19 @@ source /opt/intel/oneapi/setvars.sh
export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
echo "UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=${UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS}"
echo "ONEAPI_DEVICE_SELECTOR=${ONEAPI_DEVICE_SELECTOR}"
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 ${SPLIT_MODE}"
echo "ONEAPI_DEVICE_SELECTOR=${ONEAPI_DEVICE_SELECTOR}"
else
echo "Use all Intel GPUs, including iGPU & dGPU"
echo "Use Intel GPUs: ${SYCL_DEVICES}"
GPUS_SETTING="-sm ${SPLIT_MODE}"
fi
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
echo "run cmd: ZES_ENABLE_SYSMAN=1 ${BIN_FILE} -m ${MODEL_FILE} -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --device ${SYCL_DEVICES} --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} --device ${SYCL_DEVICES} --mmap --host 0.0.0.0 --port 8000
examples/sycl/test.sh
+12 -4
View File
@@ -12,6 +12,7 @@ This script processes files with specified options.
Options:
-h, --help Display this help message and exit.
-d, --device <value> Set SYCL devices (default: SYCL0).
-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.
@@ -42,10 +43,16 @@ MODEL_FILE=../models/llama-2-7b.Q4_0.gguf
NGL=99
CONTEXT=4096
GGML_SYCL_DEVICE=-1
SYCL_DEVICES="SYCL0"
SPLIT_MODE=layer
LOG_VERBOSE=3
while [[ $# -gt 0 ]]; do
case "$1" in
-d|--device)
SYCL_DEVICES="$2"
shift
shift
;;
-c|--context)
CONTEXT=$2
# Shift twice to consume both the option flag and its value
@@ -115,16 +122,17 @@ source /opt/intel/oneapi/setvars.sh
export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
echo "UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=${UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS}"
echo "ONEAPI_DEVICE_SELECTOR=${ONEAPI_DEVICE_SELECTOR}"
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 ${SPLIT_MODE}"
echo "ONEAPI_DEVICE_SELECTOR=${ONEAPI_DEVICE_SELECTOR}"
else
echo "Use all Intel GPUs, including iGPU & dGPU"
echo "Use Intel GPUs: ${SYCL_DEVICES}"
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
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} --device ${SYCL_DEVICES} --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} --device ${SYCL_DEVICES} --mmap
examples/sycl/win-start-svr.bat
+23 -5
View File
@@ -13,6 +13,7 @@ set "MODEL_FILE=..\models\Qwen3.5-4B-Q4_0.gguf"
set "NGL=99"
set "CONTEXT=4096"
set "GGML_SYCL_DEVICE=-1"
set "SYCL_DEVICES=SYCL0"
set "SPLIT_MODE=layer"
set "LOG_VERBOSE=3"
@@ -36,6 +37,21 @@ if /I "%~1"=="--context" (
goto parse_args
)
if /I "%~1"=="-d" (
if "%~2"=="" goto missing_value
set "SYCL_DEVICES=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--device" (
if "%~2"=="" goto missing_value
set "SYCL_DEVICES=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-m" (
if "%~2"=="" goto missing_value
set "MODEL_FILE=%~2"
@@ -130,6 +146,7 @@ echo This script processes files with specified options.
echo.
echo Options:
echo -h, --help Display this help message and exit.
echo -d, --device ^<value^> Set SYCL devices (default: SYCL0).
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.
@@ -160,19 +177,20 @@ 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%
echo ONEAPI_DEVICE_SELECTOR=%ONEAPI_DEVICE_SELECTOR%
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%"
echo ONEAPI_DEVICE_SELECTOR=%ONEAPI_DEVICE_SELECTOR%
) else (
echo Use all Intel GPUs, including iGPU ^& dGPU
) else (
echo Use Intel GPUs: %SYCL_DEVICES%
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
echo run cmd: ZES_ENABLE_SYSMAN=1 %BIN_FILE% -m "%MODEL_FILE%" -ngl %NGL% -s %SEED% -c %CONTEXT% %GPUS_SETTING% -lv %LOG_VERBOSE% --device %SYCL_DEVICES% --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
%BIN_FILE% -m "%MODEL_FILE%" -ngl %NGL% -s %SEED% -c %CONTEXT% %GPUS_SETTING% -lv %LOG_VERBOSE% --device "%SYCL_DEVICES%" --mmap --host 0.0.0.0 --port 8000
endlocal
examples/sycl/win-test.bat
+24 -5
View File
@@ -19,6 +19,7 @@ set "MODEL_FILE=..\models\llama-2-7b.Q4_0.gguf"
set "NGL=99"
set "CONTEXT=4096"
set "GGML_SYCL_DEVICE=-1"
set "SYCL_DEVICES=SYCL0"
set "SPLIT_MODE=layer"
set "LOG_VERBOSE=3"
@@ -42,6 +43,21 @@ if /I "%~1"=="--context" (
goto parse_args
)
if /I "%~1"=="-d" (
if "%~2"=="" goto missing_value
set "SYCL_DEVICES=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="--device" (
if "%~2"=="" goto missing_value
set "SYCL_DEVICES=%~2"
shift
shift
goto parse_args
)
if /I "%~1"=="-p" (
if "%~2"=="" goto missing_value
set "INPUT_PROMPT=%~2"
@@ -151,6 +167,7 @@ echo This script processes files with specified options.
echo.
echo Options:
echo -h, --help Display this help message and exit.
echo -d, --device ^<value^> Set SYCL devices (default: SYCL0).
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.
@@ -182,19 +199,21 @@ 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%
echo ONEAPI_DEVICE_SELECTOR=%ONEAPI_DEVICE_SELECTOR%
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%"
echo ONEAPI_DEVICE_SELECTOR=%ONEAPI_DEVICE_SELECTOR%
) else (
echo Use all Intel GPUs, including iGPU ^& dGPU
)
else (
echo Use Intel GPUs: %SYCL_DEVICES%
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
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% --device %SYCL_DEVICES% --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
%BIN_FILE% -m "%MODEL_FILE%" -no-cnv -p "%INPUT_PROMPT%" -n 200 -e -ngl %NGL% -s %SEED% -c %CONTEXT% %GPUS_SETTING% -lv %LOG_VERBOSE% --device "%SYCL_DEVICES%" --mmap
endlocal