fix(runner.sh): enable eager mode (disabling cuda graph)

Becasue of this warning, I tried to disable cuda graph:

Capturing cudagraphs for decoding. This may lead to unexpected consequences if the model is not static. To run the model in eager mode, set 'enforce_eager=True' or use '--enforce-eager' in the CLI.

runner.sh

@@ -51,4 +51,5 @@ python -u /app/openai_compatible_api_server.py \
     --max-num-batched-tokens 32768 \
     --max-model-len 32768 \
     --dtype float16 \
+    --enforce-eager \
     --gpu-memory-utilization 0.9