[SYCL] replace llama-cli by llama-completion to rm the impact to test script (#18290)
* replace llama-cli by llama-completion to rm the impact to test script * Update examples/sycl/run-llama2.sh Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update examples/sycl/run-llama2.sh Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update examples/sycl/run-llama3.sh Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update examples/sycl/run-llama3.sh Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update examples/sycl/win-run-llama2.bat Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update examples/sycl/win-run-llama3.bat Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
co-authored by
Sigbjørn Skjæret
Neo Zhang Jianyu
parent
96e33a814e
commit
a6a552e4ec
@@ -22,9 +22,9 @@ 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-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT} -mg $GGML_SYCL_DEVICE -sm none
|
||||
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-completion -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT} -mg $GGML_SYCL_DEVICE -sm none
|
||||
|
||||
else
|
||||
#use multiple GPUs with same max compute units
|
||||
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT}
|
||||
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-completion -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT}
|
||||
fi
|
||||
|
||||
Reference in New Issue
Block a user