happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[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:
Neo Zhang 2025-12-23 12:59:12 +08:00 committed by GitHub
parent 96e33a814e
commit a6a552e4ec
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/sycl/run-llama2.sh
View File

@ -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

4
examples/sycl/run-llama3.sh
View File

@ -24,8 +24,8 @@ export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
if [ $# -gt 0 ]; then
GGML_SYCL_DEVICE=$1
echo "Using $GGML_SYCL_DEVICE as the main GPU"
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

2
examples/sycl/win-run-llama2.bat
View File

@ -8,4 +8,4 @@ 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
.\build\bin\llama-cli.exe -m models\llama-2-7b.Q4_0.gguf -p %INPUT2% -n 400 -e -ngl 99 -s 0
.\build\bin\llama-completion.exe -m models\llama-2-7b.Q4_0.gguf -no-cnv -p %INPUT2% -n 400 -e -ngl 99 -s 0

2
examples/sycl/win-run-llama3.bat
View File

@ -8,4 +8,4 @@ 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
.\build\bin\llama-cli.exe -m models\Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -p %INPUT2% -n 400 -s 0 -e -ngl 99
.\build\bin\llama-completion.exe -m models\Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -no-cnv -p %INPUT2% -n 400 -s 0 -e -ngl 99