tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-20 09:37:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

set context default to avoid memory issue, update guide

Browse Source
This commit is contained in:
arthw
2024-09-14 09:01:05 +08:00
parent feff4aa846
commit 8241151f16
2 changed files with 12 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/sycl/run-llama2.sh
View File

@ -11,16 +11,17 @@ source /opt/intel/oneapi/setvars.sh
#ZES_ENABLE_SYSMAN=1, Support to get free memory of GPU by sycl::aspect::ext_intel_free_memory. Recommended to use when --split-mode = layer.
INPUT_PROMPT="Building a website can be done in 10 simple steps:\nStep 1:"
MODEL_FILE=llama-2-7b.Q4_0.gguf
MODEL_FILE=models/llama-2-7b.Q4_0.gguf
NGL=33
CONEXT=8192
if [ $# -gt 0 ]; then
GGML_SYCL_DEVICE=$1
echo "use $GGML_SYCL_DEVICE as main GPU"
#use signle GPU only
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -mg $GGML_SYCL_DEVICE -sm none
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONEXT} -mg $GGML_SYCL_DEVICE -sm none
else
#use multiple GPUs with same max compute units
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONEXT}
fi