[CPU] Replace OMP initialization (#36487)

Signed-off-by: Anton Ivanov <anton.ivanov@cambridgegreys.com>
This commit is contained in:
Anton Ivanov
2026-04-03 11:42:43 +01:00
committed by GitHub
parent 25f2b55319
commit abebd9323d
7 changed files with 321 additions and 426 deletions

View File

@@ -23,22 +23,22 @@ if [ "$failed_req" -ne 0 ]; then
exit 1
fi
echo "--- DP+TP"
vllm serve meta-llama/Llama-3.2-3B-Instruct -tp=2 -dp=2 --max-model-len=4096 &
server_pid=$!
timeout 600 bash -c "until curl localhost:8000/v1/models > /dev/null 2>&1; do sleep 1; done" || exit 1
vllm bench serve \
--backend vllm \
--dataset-name random \
--model meta-llama/Llama-3.2-3B-Instruct \
--num-prompts 20 \
--result-dir ./test_results \
--result-filename dp_pp.json \
--save-result \
--endpoint /v1/completions
kill -s SIGTERM $server_pid; wait $server_pid || true
failed_req=$(jq '.failed' ./test_results/dp_pp.json)
if [ "$failed_req" -ne 0 ]; then
echo "Some requests were failed!"
exit 1
fi
#echo "--- DP+TP"
#vllm serve meta-llama/Llama-3.2-3B-Instruct -tp=2 -dp=2 --max-model-len=4096 &
#server_pid=$!
#timeout 600 bash -c "until curl localhost:8000/v1/models > /dev/null 2>&1; do sleep 1; done" || exit 1
#vllm bench serve \
# --backend vllm \
# --dataset-name random \
# --model meta-llama/Llama-3.2-3B-Instruct \
# --num-prompts 20 \
# --result-dir ./test_results \
# --result-filename dp_pp.json \
# --save-result \
# --endpoint /v1/completions
#kill -s SIGTERM $server_pid; wait $server_pid || true
#failed_req=$(jq '.failed' ./test_results/dp_pp.json)
#if [ "$failed_req" -ne 0 ]; then
# echo "Some requests were failed!"
# exit 1
#fi