tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-16 23:57:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

rename llama|main -> llama-cli; consistent RPM bin prefixes

Browse Source
This commit is contained in:
Olivier Chafik
2024-06-10 15:34:14 +01:00
parent 347f30803f
commit 5265c15d4c
51 changed files with 142 additions and 144 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/sycl/run-llama2.sh
View File

@ -23,15 +23,15 @@ fi
if [ $GGML_SYCL_SINGLE_GPU -eq 1 ]; then
echo "use $GGML_SYCL_DEVICE as main GPU"
#use signle GPU only
ZES_ENABLE_SYSMAN=1 ./build/bin/llama -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0 -mg $GGML_SYCL_DEVICE -sm none
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0 -mg $GGML_SYCL_DEVICE -sm none
else
#use multiple GPUs with same max compute units
ZES_ENABLE_SYSMAN=1 ./build/bin/llama -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0
fi
#use main GPU only
#ZES_ENABLE_SYSMAN=1 ./build/bin/llama -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0 -mg $GGML_SYCL_DEVICE -sm none
#ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0 -mg $GGML_SYCL_DEVICE -sm none
#use multiple GPUs with same max compute units
#ZES_ENABLE_SYSMAN=1 ./build/bin/llama -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0
#ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m models/llama-2-7b.Q4_0.gguf -p "${INPUT2}" -n 400 -e -ngl 33 -s 0