diff --git a/.github/workflows/_e2e_nightly_multi_node.yaml b/.github/workflows/_e2e_nightly_multi_node.yaml
index 71ab5165..fa3659e5 100644
--- a/.github/workflows/_e2e_nightly_multi_node.yaml
+++ b/.github/workflows/_e2e_nightly_multi_node.yaml
@@ -32,7 +32,7 @@ on:
         description: how many pods will be pulled up via lws.yaml, indicates number of nodes we need
       vllm_version:
         required: false
-        default: "v0.14.0"
+        default: "v0.14.1"
         type: string
         description: vllm version to use
       vllm_ascend_remote_url:
diff --git a/.github/workflows/nightly_test_a2.yaml b/.github/workflows/nightly_test_a2.yaml
index 4817dbd1..bef88138 100644
--- a/.github/workflows/nightly_test_a2.yaml
+++ b/.github/workflows/nightly_test_a2.yaml
@@ -66,7 +66,7 @@ jobs:
             tests: tests/e2e/nightly/single_node/ops/multicard_ops_a2/
     uses: ./.github/workflows/_e2e_nightly_single_node.yaml
     with:
-      vllm: v0.14.0
+      vllm: v0.14.1
       runner: ${{ matrix.test_config.os }}
       tests: ${{ matrix.test_config.tests }}
       name: ${{ matrix.test_config.name }}
@@ -137,7 +137,7 @@ jobs:
               - Qwen3-Omni-30B-A3B-Instruct
     uses: ./.github/workflows/_e2e_nightly_single_node_models.yaml
     with:
-      vllm: v0.14.0
+      vllm: v0.14.1
       runner: ${{ matrix.test_config.os }}
       model_list: ${{ toJson(matrix.test_config.model_list) }}
       image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/cann:8.5.0-910b-ubuntu22.04-py3.11'
diff --git a/.github/workflows/nightly_test_a3.yaml b/.github/workflows/nightly_test_a3.yaml
index db604326..b4963cdc 100644
--- a/.github/workflows/nightly_test_a3.yaml
+++ b/.github/workflows/nightly_test_a3.yaml
@@ -161,7 +161,7 @@ jobs:
             tests: tests/e2e/nightly/single_node/models/test_deepseek_v3_2_w8a8.py
     uses: ./.github/workflows/_e2e_nightly_single_node.yaml
     with:
-      vllm: v0.14.0
+      vllm: v0.14.1
       runner: ${{ matrix.test_config.os }}
       image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a3'
       tests: ${{ matrix.test_config.tests }}
@@ -181,7 +181,7 @@ jobs:
     uses: ./.github/workflows/_e2e_nightly_single_node.yaml
     with:
       runner: ${{ matrix.test_config.os }}
-      vllm: v0.14.0
+      vllm: v0.14.1
       image: 'swr.cn-southwest-2.myhuaweicloud.com/base_image/ascend-ci/vllm-ascend:nightly-a3'
       tests: ${{ matrix.test_config.tests }}
       name: ${{ matrix.test_config.name }}
diff --git a/.github/workflows/pr_test_full.yaml b/.github/workflows/pr_test_full.yaml
index 03866afa..5e875325 100644
--- a/.github/workflows/pr_test_full.yaml
+++ b/.github/workflows/pr_test_full.yaml
@@ -75,7 +75,7 @@ jobs:
     name: e2e-full
     strategy:
       matrix:
-        vllm_version: [d68209402ddab3f54a09bc1f4de9a9495a283b60, v0.14.0]
+        vllm_version: [d68209402ddab3f54a09bc1f4de9a9495a283b60, v0.14.1]
     needs: [changes]
     if: ${{ needs.changes.outputs.e2e_tracker == 'true' }}
     uses: ./.github/workflows/_e2e_test.yaml
diff --git a/.github/workflows/pr_test_light.yaml b/.github/workflows/pr_test_light.yaml
index 44043665..390f6343 100644
--- a/.github/workflows/pr_test_light.yaml
+++ b/.github/workflows/pr_test_light.yaml
@@ -85,7 +85,7 @@ jobs:
     if: ${{ needs.lint.result == 'success' && (needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.ut_tracker == 'true') }}
     strategy:
       matrix:
-        vllm_version: [d68209402ddab3f54a09bc1f4de9a9495a283b60, v0.14.0]
+        vllm_version: [d68209402ddab3f54a09bc1f4de9a9495a283b60, v0.14.1]
     uses: ./.github/workflows/_unit_test.yaml
     with:
       vllm: ${{ matrix.vllm_version }}
@@ -97,7 +97,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [d68209402ddab3f54a09bc1f4de9a9495a283b60, v0.14.0]
+        vllm_version: [d68209402ddab3f54a09bc1f4de9a9495a283b60, v0.14.1]
     # Note (yikun): If CI resource are limited we can split job into two chain jobs
     needs: [lint, changes]
     # only trigger e2e test after lint passed and the change is e2e related with pull request.
diff --git a/.github/workflows/schedule_test_benchmarks.yaml b/.github/workflows/schedule_test_benchmarks.yaml
index 173b671b..8585670d 100644
--- a/.github/workflows/schedule_test_benchmarks.yaml
+++ b/.github/workflows/schedule_test_benchmarks.yaml
@@ -51,7 +51,7 @@ jobs:
     strategy:
       matrix:
         include:
-          - vllm_branch: v0.14.0
+          - vllm_branch: v0.14.1
             vllm_ascend_branch: main
       max-parallel: 1
     container:
diff --git a/Dockerfile b/Dockerfile
index c6ec255c..02e28209 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -48,7 +48,7 @@ RUN pip config set global.index-url ${PIP_INDEX_URL}
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=v0.14.0
+ARG VLLM_TAG=v0.14.1
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
diff --git a/Dockerfile.310p b/Dockerfile.310p
index f72f52dc..07b97bc1 100644
--- a/Dockerfile.310p
+++ b/Dockerfile.310p
@@ -40,7 +40,7 @@ RUN pip config set global.index-url ${PIP_INDEX_URL}
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=v0.14.0
+ARG VLLM_TAG=v0.14.1
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
diff --git a/Dockerfile.310p.openEuler b/Dockerfile.310p.openEuler
index 3d943327..abf70a88 100644
--- a/Dockerfile.310p.openEuler
+++ b/Dockerfile.310p.openEuler
@@ -36,7 +36,7 @@ COPY . /vllm-workspace/vllm-ascend/
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=v0.14.0
+ARG VLLM_TAG=v0.14.1
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
diff --git a/Dockerfile.a3 b/Dockerfile.a3
index 768f861a..7688c14d 100644
--- a/Dockerfile.a3
+++ b/Dockerfile.a3
@@ -47,7 +47,7 @@ RUN apt-get update -y && \
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=v0.14.0
+ARG VLLM_TAG=v0.14.1
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
diff --git a/Dockerfile.a3.openEuler b/Dockerfile.a3.openEuler
index d66e031e..6129adc7 100644
--- a/Dockerfile.a3.openEuler
+++ b/Dockerfile.a3.openEuler
@@ -50,7 +50,7 @@ RUN yum update -y && \
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=v0.14.0
+ARG VLLM_TAG=v0.14.1
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
diff --git a/Dockerfile.openEuler b/Dockerfile.openEuler
index 3414de5a..7603372f 100644
--- a/Dockerfile.openEuler
+++ b/Dockerfile.openEuler
@@ -50,7 +50,7 @@ RUN yum update -y && \
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=v0.14.0
+ARG VLLM_TAG=v0.14.1
 RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
 # In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
 RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
diff --git a/docs/source/community/versioning_policy.md b/docs/source/community/versioning_policy.md
index 03cbc5a8..facc2c65 100644
--- a/docs/source/community/versioning_policy.md
+++ b/docs/source/community/versioning_policy.md
@@ -54,7 +54,7 @@ For main branch of vLLM Ascend, we usually make it compatible with the latest vL
 
 | vLLM Ascend | vLLM         | Python           | Stable CANN | PyTorch/torch_npu  |
 |-------------|--------------|------------------|-------------|--------------------|
-|     main    | d68209402ddab3f54a09bc1f4de9a9495a283b60, v0.14.0 tag | >= 3.10, < 3.12   | 8.5.0 | 2.9.0 / 2.9.0 |
+|     main    | d68209402ddab3f54a09bc1f4de9a9495a283b60, v0.14.1 tag | >= 3.10, < 3.12   | 8.5.0 | 2.9.0 / 2.9.0 |
 
 ## Release cadence
 
diff --git a/docs/source/conf.py b/docs/source/conf.py
index 603673b8..e89ceeee 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -77,7 +77,7 @@ myst_substitutions = {
     # CANN image tag
     "cann_image_tag": "8.5.0-910b-ubuntu22.04-py3.11",
     # vllm version in ci
-    "ci_vllm_version": "v0.14.0",
+    "ci_vllm_version": "v0.14.1",
 }
 
 # For cross-file header anchors