diff --git a/.github/workflows/bot_pr_create.yaml b/.github/workflows/bot_pr_create.yaml
index fb48e0f8..235d0c7d 100644
--- a/.github/workflows/bot_pr_create.yaml
+++ b/.github/workflows/bot_pr_create.yaml
@@ -37,7 +37,7 @@ jobs:
     steps:
       - name: Get vLLM version
         run: |
-          VLLM_COMMIT=6a9cceb219fcbd6b1eb540ddfdc77ec160f0e209
+          VLLM_COMMIT=ed359c497a728f08b5b41456c07a688ccd510fbc
           echo "VLLM_COMMIT=https://github.com/vllm-project/vllm/commit/$VLLM_COMMIT" >> "$GITHUB_ENV"
 
       - name: Checkout repository
diff --git a/.github/workflows/dockerfiles/Dockerfile.lint b/.github/workflows/dockerfiles/Dockerfile.lint
index 2164e8db..ffd1e7b8 100644
--- a/.github/workflows/dockerfiles/Dockerfile.lint
+++ b/.github/workflows/dockerfiles/Dockerfile.lint
@@ -27,7 +27,7 @@ RUN apt-get update -y && \
 
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
 # For lint purpose, actually we need make a main2main matching.
-ARG VLLM_COMMIT=6a9cceb219fcbd6b1eb540ddfdc77ec160f0e209
+ARG VLLM_COMMIT=ed359c497a728f08b5b41456c07a688ccd510fbc
 RUN git clone $VLLM_REPO /vllm-workspace/vllm && \
     cd /vllm-workspace/vllm && \
     git checkout $VLLM_COMMIT
diff --git a/.github/workflows/pr_test_full.yaml b/.github/workflows/pr_test_full.yaml
index deca948d..2ad78980 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: [6a9cceb219fcbd6b1eb540ddfdc77ec160f0e209, v0.18.0]
+        vllm_version: [ed359c497a728f08b5b41456c07a688ccd510fbc, v0.18.0]
     needs: [changes]
     if: ${{ needs.changes.outputs.e2e_tracker == 'true' || 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 3e705778..6bdf2425 100644
--- a/.github/workflows/pr_test_light.yaml
+++ b/.github/workflows/pr_test_light.yaml
@@ -41,7 +41,7 @@ jobs:
   lint:
     uses: ./.github/workflows/_pre_commit.yml
     with:
-      vllm: 6a9cceb219fcbd6b1eb540ddfdc77ec160f0e209
+      vllm: ed359c497a728f08b5b41456c07a688ccd510fbc
   changes:
     runs-on: linux-aarch64-a2b3-0
     outputs:
@@ -90,7 +90,7 @@ jobs:
     if: ${{ needs.lint.result == 'success' && (needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.ut_tracker == 'true') }}
     strategy:
       matrix:
-        vllm_version: [6a9cceb219fcbd6b1eb540ddfdc77ec160f0e209, v0.18.0]
+        vllm_version: [ed359c497a728f08b5b41456c07a688ccd510fbc, v0.18.0]
     uses: ./.github/workflows/_unit_test.yaml
     with:
       vllm: ${{ matrix.vllm_version }}
@@ -102,7 +102,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [6a9cceb219fcbd6b1eb540ddfdc77ec160f0e209, v0.18.0]
+        vllm_version: [ed359c497a728f08b5b41456c07a688ccd510fbc, v0.18.0]
     # 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_codecov_refresh.yaml b/.github/workflows/schedule_codecov_refresh.yaml
index 3c4b8e94..83ddaf97 100644
--- a/.github/workflows/schedule_codecov_refresh.yaml
+++ b/.github/workflows/schedule_codecov_refresh.yaml
@@ -33,7 +33,7 @@ jobs:
     name: refresh codecov
     strategy:
       matrix:
-        vllm_version: [6a9cceb219fcbd6b1eb540ddfdc77ec160f0e209]
+        vllm_version: [ed359c497a728f08b5b41456c07a688ccd510fbc]
     uses: ./.github/workflows/_unit_test.yaml
     with:
       vllm: ${{ matrix.vllm_version }}
diff --git a/docs/source/community/versioning_policy.md b/docs/source/community/versioning_policy.md
index 49b54958..24ada475 100644
--- a/docs/source/community/versioning_policy.md
+++ b/docs/source/community/versioning_policy.md
@@ -59,7 +59,7 @@ 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    | 6a9cceb219fcbd6b1eb540ddfdc77ec160f0e209, v0.18.0 tag | >= 3.10, < 3.12   | 8.5.0 | 2.9.0 / 2.9.0 |
+|     main    | ed359c497a728f08b5b41456c07a688ccd510fbc, v0.18.0 tag | >= 3.10, < 3.12   | 8.5.0 | 2.9.0 / 2.9.0 |
 
 ## Release cadence
 
diff --git a/vllm_ascend/ascend_config.py b/vllm_ascend/ascend_config.py
index 158db86d..b9ee5ae9 100644
--- a/vllm_ascend/ascend_config.py
+++ b/vllm_ascend/ascend_config.py
@@ -161,7 +161,7 @@ class AscendConfig:
 
     @staticmethod
     def _get_compile_ranges(compilation_config):
-        return compilation_config.compile_ranges_endpoints
+        return compilation_config.compile_ranges_endpoints or []
 
     @staticmethod
     def _set_compile_ranges(compilation_config, value):
diff --git a/vllm_ascend/ops/fused_moe/fused_moe.py b/vllm_ascend/ops/fused_moe/fused_moe.py
index af56f65f..01cd2d58 100644
--- a/vllm_ascend/ops/fused_moe/fused_moe.py
+++ b/vllm_ascend/ops/fused_moe/fused_moe.py
@@ -259,6 +259,12 @@ class AscendMoERunner(DefaultMoERunner):
         else:
             self.moe_forward = torch.ops.vllm.moe_forward_shared
 
+    @property
+    def use_dp_chunking(self) -> bool:
+        """Ascend uses its own forward_impl path, not the FlashInfer Cutlass
+        chunked path. Always return False to stay on forward_impl."""
+        return False
+
     def forward_impl(
         self,
         layer: torch.nn.Module,