Update on "Add quantized op support to llama runner"

Summary:

Test Plan:

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: [D56197863](https://our.internmc.facebook.com/intern/diff/D56197863)

[ghstack-poisoned]

Author: larryliu0820

.ci/scripts/test_llama.sh

@@ -141,7 +141,7 @@ if [[ "${CUSTOM}" == "ON" ]]; then
   EXPORT_ARGS="${EXPORT_ARGS} --use_sdpa_with_kv_cache"
 fi
 if [[ "${QE}" == "ON" ]]; then
-  EXPORT_ARGS="${EXPORT_ARGS} --embedding-quantize '8,1024'"
+  EXPORT_ARGS="${EXPORT_ARGS} --embedding-quantize 8,1024"
 fi
 # Add dynamically linked library location
 $PYTHON_EXECUTABLE -m examples.models.llama2.export_llama ${EXPORT_ARGS}