clean up

Author: oandreeva-nv

ci/L0_backend_vllm/metrics_test/vllm_metrics_test.py

@@ -48,7 +48,7 @@ def setUp(self):
             "The capital of France is",
             "The future of AI is",
         ]
-        self.sampling_parameters = {"temperature": 0, "top_p": 1}
+        self.sampling_parameters = {"temperature": "0", "top_p": "1"}
 
     def parse_vllm_metrics(self):
         """

ci/L0_multi_gpu_vllm/multi_lora/test.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-# Copyright 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# Copyright 2024-2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
 # modification, are permitted provided that the following conditions
@@ -112,7 +112,7 @@ model_json=$(cat <<EOF
     "model":"./weights/backbone/gemma-2b",
     "disable_log_requests": true,
     "gpu_memory_utilization": 0.7,
-    "tensor_parallel_size": 1,
+    "tensor_parallel_size": 2,
     "block_size": 16,
     "enforce_eager": true,
     "enable_lora": true,