diff --git a/qa/L0_openai/test.sh b/qa/L0_openai/test.sh
index 8083c50444..a1db293436 100755
--- a/qa/L0_openai/test.sh
+++ b/qa/L0_openai/test.sh
@@ -74,6 +74,9 @@ function prepare_tensorrtllm() {
     MODEL_REPO="$2"
     ENGINE_PATH="$3"
     TENSORRTLLM_DIR="$4"
+    TRITON_BACKEND=tensorrtllm
+    XGRAMMAR_TOKENIZER_INFO_PATH=tokenizer_info/${MODEL}/xgrammar_tokenizer_info.json
+    GUIDED_DECODING_BACKEND=xgrammar
 
     mkdir -p ${MODEL_REPO}
     cp ${TENSORRTLLM_DIR}/triton_backend/all_models/inflight_batcher_llm/* "${MODEL_REPO}" -r
@@ -83,12 +86,17 @@ function prepare_tensorrtllm() {
     # 1. Generate the model's trt engines
     python3 ../generate_engine.py --model "${MODEL}" --engine_path "${ENGINE_PATH}"
 
-    # 2. Prepare model repository
+    # 2. Generate the model's xgrammar tokenizer info. In order to run on C++ backend, we need an extra step to extract tokenizer’s information into json format.
+    XGRAMMAR_TOKENIZER_INFO_DIR=tokenizer_info/${MODEL}
+    rm -rf ${XGRAMMAR_TOKENIZER_INFO_DIR}
+    python3 /app/examples/generate_xgrammar_tokenizer_info.py --model_dir ${MODEL} --output_dir ${XGRAMMAR_TOKENIZER_INFO_DIR}
+
+    # 3. Prepare model repository
     FILL_TEMPLATE="/app/tools/fill_template.py"
     python3 ${FILL_TEMPLATE} -i ${MODEL_REPO}/preprocessing/config.pbtxt tokenizer_dir:${ENGINE_PATH},triton_max_batch_size:64,preprocessing_instance_count:1,max_queue_size:0
     python3 ${FILL_TEMPLATE} -i ${MODEL_REPO}/postprocessing/config.pbtxt tokenizer_dir:${ENGINE_PATH},triton_max_batch_size:64,postprocessing_instance_count:1
     python3 ${FILL_TEMPLATE} -i ${MODEL_REPO}/tensorrt_llm_bls/config.pbtxt triton_max_batch_size:64,decoupled_mode:True,bls_instance_count:1,accumulate_tokens:False,logits_datatype:TYPE_FP32,prompt_embedding_table_data_type:TYPE_FP16
-    python3 ${FILL_TEMPLATE} -i ${MODEL_REPO}/tensorrt_llm/config.pbtxt triton_backend:tensorrtllm,triton_max_batch_size:64,decoupled_mode:True,max_beam_width:1,engine_dir:${ENGINE_PATH},batching_strategy:inflight_fused_batching,max_queue_size:0,max_queue_delay_microseconds:1000,encoder_input_features_data_type:TYPE_FP16,logits_datatype:TYPE_FP32,exclude_input_in_output:True,prompt_embedding_table_data_type:TYPE_FP16
+    python3 ${FILL_TEMPLATE} -i ${MODEL_REPO}/tensorrt_llm/config.pbtxt triton_backend:${TRITON_BACKEND},triton_max_batch_size:64,decoupled_mode:True,max_beam_width:1,engine_dir:${ENGINE_PATH},batching_strategy:inflight_fused_batching,max_queue_size:0,max_queue_delay_microseconds:1000,encoder_input_features_data_type:TYPE_FP16,logits_datatype:TYPE_FP32,exclude_input_in_output:True,prompt_embedding_table_data_type:TYPE_FP16,guided_decoding_backend:${GUIDED_DECODING_BACKEND},xgrammar_tokenizer_info_path:${XGRAMMAR_TOKENIZER_INFO_PATH}
 }
 
 function pre_test() {