Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Exclude extra TRT version-compatible models from tests #6295

Merged
merged 1 commit into from
Sep 11, 2023
Merged

Exclude extra TRT version-compatible models from tests #6295

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions qa/L0_infer_zero/test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,10 @@ rm -fr models && mkdir models
cp -r /data/inferenceserver/${REPO_VERSION}/qa_identity_model_repository/* models/. && \
cp -r /data/inferenceserver/${REPO_VERSION}/qa_ensemble_model_repository/qa_identity_model_repository/* models/.

# Remove version-compatible TensorRT models, as they require version-compatibility
# mode to be turned on when starting the server.
rm -rf models/plan_compatible*

create_nop_version_dir `pwd`/models

RET=0
Expand Down
14 changes: 10 additions & 4 deletions qa/L0_nullchar_string/test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,16 +40,22 @@ fi

export CUDA_VISIBLE_DEVICES=0

CLIENT_LOG="./client.log"
DATADIR=/data/inferenceserver/${REPO_VERSION}/qa_identity_model_repository
MODELS="graphdef_nobatch_zero_1_object savedmodel_nobatch_zero_1_object"
NULLCHAR_CLIENT_PY=nullchar_string_client.py
CLIENT_LOG="./client.log"

SERVER=/opt/tritonserver/bin/tritonserver
SERVER_ARGS="--model-repository=$DATADIR"
SERVER_ARGS="--model-repository=models"
SERVER_LOG="./inference_server.log"
source ../common/util.sh

rm -f $CLIENT_LOG $SERVER_LOG
rm -f $CLIENT_LOG $SERVER_LOG models

mkdir -p models
for MODEL in $MODELS; do
cp -r $DATADIR/$MODEL models/.
done

run_server
if [ "$SERVER_PID" == "0" ]; then
Expand All @@ -65,7 +71,7 @@ set +e
# Ignore ONNX backend because even though ONNX supports string data type,
# strings that contain null character in the middle is not allowed.
# https://github.com/microsoft/onnxruntime/issues/2284
for MODEL in graphdef_nobatch_zero_1_object savedmodel_nobatch_zero_1_object; do
for MODEL in $MODELS; do
python $NULLCHAR_CLIENT_PY -m $MODEL -v >>$CLIENT_LOG 2>&1
if [ $? -ne 0 ]; then
RET=1
Expand Down