Skip to content

test: Skip Torch-TensorRT QA model generation on compute capability 10.7 #8914

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

Closed
mc-nv wants to merge 1 commit into from
+5 −1
Closed

test: Skip Torch-TensorRT QA model generation on compute capability 10.7 #8914

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
6 changes: 5 additions & 1 deletion qa/common/gen_qa_model_repository
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -283,7 +283,11 @@ python3 $TRITON_MDLS_SRC_DIR/gen_qa_implicit_models.py --libtorch --variable --m
chmod -R 777 $TRITON_MDLS_QA_VARIABLE_SEQUENCE_IMPLICIT_MODEL
python3 $TRITON_MDLS_SRC_DIR/gen_qa_dyna_sequence_models.py --libtorch --models_dir=$TRITON_MDLS_QA_DYNA_SEQUENCE_MODEL
chmod -R 777 $TRITON_MDLS_QA_DYNA_SEQUENCE_MODEL
if [ -z "$MODEL_TYPE" ] || [ "$MODEL_TYPE" != "igpu" ]; then
# TRI-1625: exclude Torch-TensorRT model generation on 10.7 compute resources.
COMPUTE_CAP=\$(nvidia-smi --query-gpu=compute_cap --format=csv,noheader | head -1 | tr -d '[:space:]')
if [[ "\$COMPUTE_CAP" == "10.7" ]]; then
echo "Skipping Torch-TensorRT model generation (compute capability '\$COMPUTE_CAP')"
else
Comment thread
mc-nv marked this conversation as resolved.
python3 $TRITON_MDLS_SRC_DIR/gen_qa_torchtrt_models.py --models_dir=$TRITON_MDLS_QA_TORCHTRT_MODEL
chmod -R 777 $TRITON_MDLS_QA_TORCHTRT_MODEL
fi
Expand Down
Loading