diff --git a/python/llm/dev/benchmark/all-in-one/run.py b/python/llm/dev/benchmark/all-in-one/run.py
index 721f7481380..31c3ecee8b2 100644
--- a/python/llm/dev/benchmark/all-in-one/run.py
+++ b/python/llm/dev/benchmark/all-in-one/run.py
@@ -1803,6 +1803,8 @@ def run_pipeline_parallel_gpu(repo_id,
     if 'exclude' in conf:
         excludes = conf['exclude']
     streaming = False
+    use_fp16_torch_dtype = False
+    n_gpu = 2
     if 'streaming' in conf:
         streaming = conf['streaming']
     if 'use_fp16_torch_dtype' in conf: