diff --git a/Dockerfile b/Dockerfile
index 1db0b24..0e7dbf2 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -12,7 +12,7 @@ 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==0.8.4 && \
+RUN python3 -m pip install vllm==0.8.5 && \
     python3 -m pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3
 
 # Setup for Option 2: Building the Image with the Model included
@@ -47,4 +47,4 @@ RUN --mount=type=secret,id=HF_TOKEN,required=false \
     fi
 
 # Start the handler
-CMD ["python3", "/src/handler.py"]
\ No newline at end of file
+CMD ["python3", "/src/handler.py"]