diff --git a/benchmarks/benchmark_serving.py b/benchmarks/benchmark_serving.py
index 2c2d69da..9c3fed48 100644
--- a/benchmarks/benchmark_serving.py
+++ b/benchmarks/benchmark_serving.py
@@ -17,6 +17,10 @@ On the client side, run:
         --dataset-path <path to dataset> \
         --request-rate <request_rate> \ # By default <request_rate> is inf
         --num-prompts <num_prompts> # By default <num_prompts> is 1000
+        
+    when using tgi backend, add
+        --endpoint /generate_stream
+    to the end of the command above.
 """
 import argparse
 import asyncio
diff --git a/benchmarks/launch_tgi_server.sh b/benchmarks/launch_tgi_server.sh
index 64d3c4f4..f491c90d 100755
--- a/benchmarks/launch_tgi_server.sh
+++ b/benchmarks/launch_tgi_server.sh
@@ -4,7 +4,7 @@ PORT=8000
 MODEL=$1
 TOKENS=$2
 
-docker run --gpus all --shm-size 1g -p $PORT:80 \
+docker run -e HF_TOKEN=$HF_TOKEN --gpus all --shm-size 1g -p $PORT:80 \
            -v $PWD/data:/data \
            ghcr.io/huggingface/text-generation-inference:1.4.0 \
            --model-id $MODEL \