Revert "Enabling model caching."

2025-02-18 10:45:47 -08:00
parent d7e9c49fe4
commit 2b1d618287
1 changed files with 0 additions and 3 deletions
@@ -24,10 +24,7 @@ class vLLMEngine:
    def __init__(self, engine = None):
        load_dotenv() # For local development
        self.engine_args = get_engine_args()
-        if os.getenv("MODEL_CACHE_ENABLE"):
-            self.engine_args.model = f"/runpod/cache/model/{os.getenv('MODEL_NAME')}/main"
        logging.info(f"Engine args: {self.engine_args}")
-        
        self.tokenizer = TokenizerWrapper(self.engine_args.tokenizer or self.engine_args.model, 
                                          self.engine_args.tokenizer_revision, 
                                          self.engine_args.trust_remote_code)