Move imports

model.py

@@ -2,9 +2,7 @@ import os
 from time import time, sleep
 from logger import logger
 import math
-import torch
-from vllm import LLM, SamplingParams
-from transformers import AutoTokenizer
+
 
 
 
@@ -51,7 +49,9 @@ def get_probablities(logprobs):
 
 mock_model_call = os.getenv('MOCK_MODEL_CALL') == 'true'
 if not mock_model_call:
-    use_conda = os.getenv('USE_CONDA', "false") == "true"
+    import torch
+    from vllm import LLM, SamplingParams
+    from transformers import AutoTokenizer
     model_path = os.getenv('MODEL_PATH')#"granite-guardian-3b-pipecleaner-r241024a"
     sampling_params = SamplingParams(temperature=0.0, logprobs=nlogprobs)
     model = LLM(model=model_path, tensor_parallel_size=1)