diff --git a/Dockerfile b/Dockerfile
index e59a03e..332bf48 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]==0.17.1" --extra-index-url https://download.pytorch.org/whl/cu129
+    uv pip install --system "vllm[flashinfer]==0.18.1" --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/vllm-loadbalancer-ep.code-workspace b/vllm-loadbalancer-ep.code-workspace
new file mode 100644
index 0000000..c29e4b2
--- /dev/null
+++ b/vllm-loadbalancer-ep.code-workspace
@@ -0,0 +1,11 @@
+{
+	"folders": [
+		{
+			"path": "../vllm-loadbalancer-ep"
+		},
+		{
+			"path": "."
+		}
+	],
+	"settings": {}
+}
\ No newline at end of file