diff --git a/ChatQnA/benchmark/performance/helm_charts/deployment.py b/ChatQnA/benchmark/performance/helm_charts/deployment.py index e5ae0a838..0c7649821 100644 --- a/ChatQnA/benchmark/performance/helm_charts/deployment.py +++ b/ChatQnA/benchmark/performance/helm_charts/deployment.py @@ -69,7 +69,7 @@ def generate_yaml(num_nodes, mode="oob", with_rerank="True"): { "name": "llm-dependency-deploy", "args": [ - {"name": "--model-id", "value": '$(LLM_MODEL_ID)'}, + {"name": "--model-id", "value": "$(LLM_MODEL_ID)"}, {"name": "--max-input-length", "value": 1280}, {"name": "--max-total-tokens", "value": 2048}, {"name": "--max-batch-total-tokens", "value": 35536},