fix issues

Dockerfile

@@ -12,11 +12,11 @@ RUN --mount=type=cache,target=/root/.cache/pip \
     python3 -m pip install --upgrade -r /requirements.txt
 
 # Install vLLM (switching back to pip installs since issues that required building fork are fixed and space optimization is not as important since caching) and FlashInfer 
-RUN python3 -m pip install vllm==0.9.1 && \
+RUN python3 -m pip install vllm==0.10.0 && \
     python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3
 
 # Setup for Option 2: Building the Image with the Model included
-ARG MODEL_NAME="openai/gpt-oss-120b"
+ARG MODEL_NAME=""
 ARG TOKENIZER_NAME=""
 ARG BASE_PATH="/runpod-volume"
 ARG QUANTIZATION=""