Skip to content
This repository has been archived by the owner on Aug 30, 2024. It is now read-only.

Commit

Permalink
Update cpp_graph_inference.sh
Browse files Browse the repository at this point in the history
  • Loading branch information
intellinjun authored May 24, 2024
1 parent 506040a commit a0f4747
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion .github/workflows/scripts/models/cpp_graph_inference.sh
Original file line number Diff line number Diff line change
Expand Up @@ -148,7 +148,7 @@ function main() {
$infer_cmd --seed 1234 -t $cores_per_instance -b 2047 -c ${ctx} -n ${output} -m ${model}-${precision}.bin -p "$prompt" 2>&1 | tee ${WORKING_DIR}/${logs_file} || true &
monitor
if [[ ${precision} == "q4_j_b32" ]]&&[[ ${input} == "1024" ]]&&[[ "${model}" == "llama3-8b" ]]; then
python ./scripts/cal_acc.py --model_name ${input_model} --init_from_bin ${model}-${precision}.bin --tasks lambada_openai --batch_size 8 2>&1 | tee -a ${WORKING_DIR}/${logs_file}
OMP_NUM_THREADS=56 numactl -l -C 0-55 python ./scripts/cal_acc.py --model_name ${input_model} --init_from_bin ${model}-${precision}.bin --tasks lambada_openai --batch_size 8 2>&1 | tee -a ${WORKING_DIR}/${logs_file}
else
echo "-------- Inference End --------"
fi
Expand Down

0 comments on commit a0f4747

Please sign in to comment.