diff --git a/Dockerfile b/Dockerfile
index 6bb5c46..842ca2e 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -5,9 +5,9 @@ RUN apt-get update -y \
 
 RUN ldconfig /usr/local/cuda-12.9/compat/
 
-# Install vLLM with FlashInfer - use CUDA 12.8 PyTorch wheels (compatible with vLLM 0.15.1)
+# Install vLLM with FlashInfer from the CUDA 12.9 wheel index.
 RUN python3 -m pip install --upgrade pip && \
-    python3 -m pip install "vllm[flashinfer]==0.16.0" --extra-index-url https://download.pytorch.org/whl/cu129
+    python3 -m pip install "vllm[flashinfer]==0.17.0" --extra-index-url https://download.pytorch.org/whl/cu129