diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml
index df2735fefeedb..20f3ce1adb46d 100644
--- a/.buildkite/test-pipeline.yaml
+++ b/.buildkite/test-pipeline.yaml
@@ -843,3 +843,10 @@ steps:
   commands:
   - export VLLM_WORKER_MULTIPROC_METHOD=spawn
   - pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large.txt --tp-size=4
+
+- label: Qwen MoE EP Test # optional
+  gpu: h200
+  optional: true
+  num_gpus: 2
+  commands:
+    - CUDA_VISIBLE_DEVICES=1,2 VLLM_ALL2ALL_BACKEND=deepep_high_throughput VLLM_USE_DEEP_GEMM=1 VLLM_LOGGING_LEVEL=DEBUG python3 /vllm-workspace/examples/offline_inference/data_parallel.py --model Qwen/Qwen1.5-MoE-A2.7B --tp-size=1  --dp-size=2 --max-model-len 2048
diff --git a/docker/Dockerfile b/docker/Dockerfile
index cfaa59868215c..977dd7a3d31d8 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -458,6 +458,14 @@ RUN --mount=type=cache,target=/root/.cache/uv bash - <<'BASH'
     fi
 BASH
 
+# Install EP kernels(pplx-kernels and DeepEP), NixL
+COPY tools/ep_kernels/install_python_libraries.sh install_python_libraries.sh
+COPY tools/install_nixl.sh install_nixl.sh
+ENV CUDA_HOME=/usr/local/cuda
+RUN export TORCH_CUDA_ARCH_LIST="${TORCH_CUDA_ARCH_LIST:-9.0a+PTX}" \
+    && bash install_python_libraries.sh \
+    && bash install_nixl.sh --force
+
 #################### vLLM installation IMAGE ####################
 
 #################### TEST IMAGE ####################