CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

enhance run script to be easy to change the parameters (#9448)

Browse Source 
Co-authored-by: arthw <14088817+arthw@users.noreply.github.com>
This commit is contained in:
Neo Zhang Jianyu
2024-09-12 17:44:17 +08:00
committed by GitHub
parent df4b7945ae
commit c9c8575a1a
1 changed files with 9 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
examples/sycl/run-llama2.sh
View File

@@ -4,33 +4,23 @@
# Copyright (C) 2024 Intel Corporation # Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: MIT # SPDX-License-Identifier: MIT
INPUT2="Building a website can be done in 10 simple steps:\nStep 1:"
source /opt/intel/oneapi/setvars.sh source /opt/intel/oneapi/setvars.sh
if [ $# -gt 0 ]; then
GGML_SYCL_DEVICE=$1
GGML_SYCL_SINGLE_GPU=1
else
GGML_SYCL_DEVICE=0
GGML_SYCL_SINGLE_GPU=0
fi
#export GGML_SYCL_DEBUG=1 #export GGML_SYCL_DEBUG=1
#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. #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.
if [ $GGML_SYCL_SINGLE_GPU -eq 1 ]; then INPUT_PROMPT="Building a website can be done in 10 simple steps:\nStep 1:"
MODEL_FILE=llama-2-7b.Q4_0.gguf
NGL=33
if [ $# -gt 0 ]; then
GGML_SYCL_DEVICE=$1
echo "use $GGML_SYCL_DEVICE as main GPU" echo "use $GGML_SYCL_DEVICE as main GPU"
#use signle GPU only #use signle GPU only
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0 -mg $GGML_SYCL_DEVICE -sm none ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -mg $GGML_SYCL_DEVICE -sm none
else else
#use multiple GPUs with same max compute units #use multiple GPUs with same max compute units
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0 ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0
fi fi
#use main GPU only
#ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0 -mg $GGML_SYCL_DEVICE -sm none
#use multiple GPUs with same max compute units
#ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0