Update inference-cpp docker (#12882)

* remove nouse run.py

* add WORKDIR /llm

docker/llm/inference-cpp/Dockerfile

@@ -91,3 +91,5 @@ RUN set -eux && \
     # Clean up unnecessary dependencies to reduce image size
     find /usr/lib/python3/dist-packages/ -name 'blinker*' -exec rm -rf {} + && \
     rm -rf /root/.cache/Cypress
+
+WORKDIR /llm/

docker/llm/inference-cpp/benchmark_llama-cpp.sh

@@ -6,13 +6,10 @@ init-llama-cpp
 # change the model_path to run
 if [[ "$DEVICE" == "Arc" || "$DEVICE" == "ARC" ]]; then
     source ipex-llm-init -g --device Arc
-    python run.py
 elif [[ "$DEVICE" == "Flex" || "$DEVICE" == "FLEX" ]]; then
     source ipex-llm-init -g --device Flex
-    python run.py
 elif [[ "$DEVICE" == "Max" || "$DEVICE" == "MAX" ]]; then
     source ipex-llm-init -g --device Max
-    python run.py
 else
     echo "Invalid DEVICE specified."
 fi