diff --git a/Dockerfile b/Dockerfile
index 1f05b31..6e55e64 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -10,7 +10,7 @@ RUN ldconfig /usr/local/cuda-12.9/compat/
 
 # Install vLLM with FlashInfer - use CUDA 12.9 PyTorch wheels
 RUN uv pip install --system "packaging>=24.2" && \
-    uv pip install --system "vllm[flashinfer]==0.19.1" --extra-index-url https://download.pytorch.org/whl/cu129
+    uv pip install --system "vllm[flashinfer]==0.20.0" --extra-index-url https://download.pytorch.org/whl/cu129
 
 # Install additional Python dependencies (after vLLM to avoid PyTorch version conflicts)
 COPY builder/requirements.txt /requirements.txt
diff --git a/src/engine.py b/src/engine.py
index 80bf72b..0fa60c9 100644
--- a/src/engine.py
+++ b/src/engine.py
@@ -285,7 +285,6 @@ class OpenAIvLLMEngine(vLLMEngine):
         self.openai_serving_render = OpenAIServingRender(
             model_config=self.llm.model_config,
             renderer=self.llm.renderer,
-            io_processor=self.llm.io_processor,
             model_registry=self.serving_models.registry,
             request_logger=None,
             chat_template=chat_template,