diff --git a/docs/source/installation.md b/docs/source/installation.md
index 0d3b54d..0319465 100644
--- a/docs/source/installation.md
+++ b/docs/source/installation.md
@@ -141,8 +141,12 @@ Then you can install `vllm` and `vllm-ascend` from **pre-built wheel**:
 ```{code-block} bash
    :substitutions:
 
-# Install vllm-project/vllm from pypi
-pip install vllm==|pip_vllm_version|
+# Install vllm-project/vllm. The newest supported version is |vllm_version|.
+# Because the version |vllm_version| has not been archived in pypi, so you need to install from source.
+git clone --depth 1 --branch |vllm_version| https://github.com/vllm-project/vllm
+cd vllm
+VLLM_TARGET_DEVICE=empty pip install -v -e .
+cd ..
 
 # Install vllm-project/vllm-ascend from pypi.
 pip install vllm-ascend==|pip_vllm_ascend_version|
diff --git a/tests/e2e/doctests/002-pip-binary-installation-test.sh b/tests/e2e/doctests/002-pip-binary-installation-test.sh
index 525f348..4aad569 100644
--- a/tests/e2e/doctests/002-pip-binary-installation-test.sh
+++ b/tests/e2e/doctests/002-pip-binary-installation-test.sh
@@ -40,21 +40,33 @@ function install_binary_test() {
     create_vllm_venv
 
     PIP_VLLM_VERSION=$(get_version pip_vllm_version)
+    VLLM_VERSION=$(get_version vllm_version)
     PIP_VLLM_ASCEND_VERSION=$(get_version pip_vllm_ascend_version)
     _info "====> Install vllm==${PIP_VLLM_VERSION} and vllm-ascend ${PIP_VLLM_ASCEND_VERSION}"
 
     # Setup extra-index-url for x86 & torch_npu dev version
     pip config set global.extra-index-url "https://download.pytorch.org/whl/cpu/ https://mirrors.huaweicloud.com/ascend/repos/pypi"
 
-    pip install vllm=="$(get_version pip_vllm_version)"
-    pip install vllm-ascend=="$(get_version pip_vllm_ascend_version)"
+    if [[ "${VLLM_VERSION} " != "v0.11.0rc3" ]]; then
+        # The vLLM version already in pypi, we install from pypi.
+        pip install vllm=="${PIP_VLLM_VERSION}"
+    else
+        # The vLLM version not in pypi, we install from source code with a specific tag.
+        git clone --depth 1 --branch "${VLLM_VERSION}" https://github.com/vllm-project/vllm
+        cd vllm
+        VLLM_TARGET_DEVICE=empty pip install -v -e .
+        cd ..
+    fi
+
+    pip install vllm-ascend=="${PIP_VLLM_ASCEND_VERSION}"
 
     pip list | grep vllm
 
     # Verify the installation
     _info "====> Run offline example test"
     pip install modelscope
-    python3 "${SCRIPT_DIR}/../../examples/offline_inference_npu.py"
+    cd ${SCRIPT_DIR}/../../examples && python3 ./offline_inference_npu.py
+    cd -
 
 }