nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 22 Packages Projects Releases Wiki Activity

create test.sh to enhance the parameters for testing, update the guide, rm useless script (#19243)

Browse Source
This commit is contained in:
Neo Zhang
2026-02-01 18:24:00 +08:00
committed by GitHub
parent 41ea26144e
commit 2634ed207a
6 changed files with 149 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/sycl/run-llama2.sh
+3 -2
View File
@@ -18,13 +18,14 @@ CONTEXT=4096
#support malloc device memory more than 4GB.
export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
LOAD_MODE='--mmap'
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-completion -m ${MODEL_FILE} -no-cnv -p "${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 ${LOAD_MODE}
else
#use multiple GPUs with same max compute units
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}
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} ${LOAD_MODE}
fi