[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
2026-04-25 14:20:14 +08:00
committed by GitHub
parent dd2914dc81
commit eddd7a13a5
9 changed files with 617 additions and 31 deletions
+5 -4
View File
@@ -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