[SYCL] Optimize Q4_0 mul_mat for Arc770, add scripts (#22291)
* opt arc770 for Q4_0 * add for Q4_0 * update the script * add help script for windows * update guide * fix format issue * convert from dos to unix for format issue * fix missed -sm parameter
This commit is contained in:
Neo Zhang
Executable
+124
@@ -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 ${MODEL_FILE} -no-cnv -p "${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} -ngl ${NGL} -s ${SEED} -c ${CONTEXT} ${GPUS_SETTING} -lv ${LOG_VERBOSE} --mmap --host 0.0.0.0 --port 8000
|
||||
|
||||
|
||||
@@ -38,7 +38,7 @@ 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
|
||||
MODEL_FILE=../models/llama-2-7b.Q4_0.gguf
|
||||
NGL=99
|
||||
CONTEXT=4096
|
||||
GGML_SYCL_DEVICE=-1
|
||||
@@ -122,9 +122,10 @@ if [ $GGML_SYCL_DEVICE -ne -1 ]; then
|
||||
export ONEAPI_DEVICE_SELECTOR="level_zero:${$GGML_SYCL_DEVICE}"
|
||||
echo "ONEAPI_DEVICE_SELECTOR=${ONEAPI_DEVICE_SELECTOR}"
|
||||
else
|
||||
echo "Use all Intel GPUs, including iGPU & dGPU"
|
||||
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 400 -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 400 -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} --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
|
||||
|
||||
|
||||
@@ -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
|
||||
|
||||
+196
-6
@@ -2,10 +2,200 @@
|
||||
:: 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%
|
||||
@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
|
||||
|
||||
|
||||
Reference in New Issue
Block a user