Debug

Author: winskuo-quic

.ci/scripts/test_qnn_static_llama.sh

@@ -33,10 +33,9 @@ echo "Creating tokenizer.bin"
 $PYTHON_EXECUTABLE -m extension.llm.tokenizer.tokenizer -t tokenizer.model -o tokenizer.bin
 
 set +e
-echo "Creating tokenizer.bin"
-# # Compile only as weight sharing is not applicable on x86
-# $PYTHON_EXECUTABLE backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleScript.test_stories_single_llama --model SM8650 --build_folder build-android/ --executorch_root . --artifact_dir . --compile_only
-# exit_code1=$?
+# Compile only as weight sharing is not applicable on x86
+$PYTHON_EXECUTABLE backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleScript.test_stories_single_llama --model SM8650 --build_folder build-android/ --executorch_root . --artifact_dir . --compile_only
+exit_code1=$?
 
 # # Checks accuracy with weight sharing disabled since x86 does not support weight sharing.
 # $PYTHON_EXECUTABLE backends/qualcomm/tests/test_qnn_delegate.py -k TestExampleScript.test_stories_single_llama --model SM8650 --build_folder build-x86_64/ --executorch_root . --artifact_dir . --enable_x86_64