common: migrate the deprecated --mmap/--no-mmap to --load-mode (#26934)
Replace the deprecated --mmap, --no-mmap, --mlock, and --direct-io flags with the unified --load-mode argument across scripts, examples, and documentation. Internal warning message and env var docs updated accordingly. Signed-off-by: Fathi Boudra <fathi.boudra@linaro.org>
This commit is contained in:
@@ -18,7 +18,7 @@ CONTEXT=4096
|
||||
#support malloc device memory more than 4GB.
|
||||
export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
|
||||
|
||||
LOAD_MODE='--mmap'
|
||||
LOAD_MODE='--load-mode auto'
|
||||
if [ $# -gt 0 ]; then
|
||||
GGML_SYCL_DEVICE=$1
|
||||
echo "use $GGML_SYCL_DEVICE as main GPU"
|
||||
|
||||
@@ -124,7 +124,7 @@ else
|
||||
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} --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
|
||||
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} --load-mode auto --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} --load-mode auto --host 0.0.0.0 --port 8000
|
||||
|
||||
|
||||
|
||||
@@ -133,6 +133,6 @@ else
|
||||
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} --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
|
||||
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} --load-mode auto "
|
||||
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} --load-mode auto
|
||||
|
||||
|
||||
@@ -7,5 +7,5 @@ set INPUT2="Building a website can be done in 10 simple steps:\nStep 1:"
|
||||
|
||||
:: support malloc device memory more than 4GB.
|
||||
set UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
|
||||
set LOAD_MODE="--mmap"
|
||||
set LOAD_MODE="--load-mode auto"
|
||||
.\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%
|
||||
|
||||
@@ -188,9 +188,9 @@ if not "%GGML_SYCL_DEVICE%"=="-1" (
|
||||
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% --device %SYCL_DEVICES% --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% --load-mode auto --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% --device "%SYCL_DEVICES%" --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%" --load-mode auto --host 0.0.0.0 --port 8000
|
||||
|
||||
endlocal
|
||||
|
||||
|
||||
@@ -211,9 +211,9 @@ else (
|
||||
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% --device %SYCL_DEVICES% --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% --load-mode auto
|
||||
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% --device "%SYCL_DEVICES%" --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%" --load-mode auto
|
||||
|
||||
endlocal
|
||||
|
||||
|
||||
Reference in New Issue
Block a user