[Misc][main2main] 0420 -> 0429

.github/workflows/_e2e_test.yaml

@@ -27,7 +27,7 @@ on:
       continue_on_error:
         required: false
         type: boolean
-        default: false
+        default: true
       # The following inputs are used by comment-triggered E2E tests (/e2e <tests>).
       # They carry space-separated pytest paths, categorized by runner type.
       # Leave empty (default) when running label-triggered full/light suites.

.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=d886c26d4d4fef7d079696beb4ece1cfb4b008a8
+ARG VLLM_COMMIT=856b15c62c8a574a1a0a289444d5b9a8120433e3
 RUN git init /vllm-workspace/vllm && \
     git -C /vllm-workspace/vllm fetch --depth 1 $VLLM_REPO $VLLM_COMMIT && \
     git -C /vllm-workspace/vllm checkout FETCH_HEAD

.github/workflows/pr_test_full.yaml

@@ -80,7 +80,7 @@ jobs:
     name: e2e-full
     strategy:
       matrix:
-        vllm_version: [d886c26d4d4fef7d079696beb4ece1cfb4b008a8, v0.19.1]
+        vllm_version: [856b15c62c8a574a1a0a289444d5b9a8120433e3, v0.19.1]
     needs: [changes]
     if: ${{ needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.e2e_tracker == true }}
     uses: ./.github/workflows/_e2e_test.yaml

.github/workflows/pr_test_light.yaml

@@ -41,7 +41,7 @@ jobs:
   lint:
     uses: ./.github/workflows/_pre_commit.yml
     with:
-      vllm: d886c26d4d4fef7d079696beb4ece1cfb4b008a8
+      vllm: 856b15c62c8a574a1a0a289444d5b9a8120433e3
   changes:
     runs-on: linux-aarch64-a2b3-0
     container:
@@ -154,7 +154,7 @@ jobs:
     if: ${{ needs.lint.result == 'success' && needs.changes.outputs.has_tests == 'true' }}
     strategy:
       matrix:
-        vllm_version: [d886c26d4d4fef7d079696beb4ece1cfb4b008a8, v0.19.1]
+        vllm_version: [856b15c62c8a574a1a0a289444d5b9a8120433e3, v0.19.1]
     uses: ./.github/workflows/_optional_smart_e2e.yaml
     with:
       vllm: ${{ matrix.vllm_version }}
@@ -164,7 +164,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [d886c26d4d4fef7d079696beb4ece1cfb4b008a8, v0.19.1]
+        vllm_version: [856b15c62c8a574a1a0a289444d5b9a8120433e3, v0.19.1]
     # 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.

docs/source/conf.py

@@ -81,7 +81,7 @@
     # CANN image tag
     "cann_image_tag": "8.5.1-910b-ubuntu22.04-py3.11",
     # vLLM commit hash for main branch
-    "main_vllm_commit": "d886c26d4d4fef7d079696beb4ece1cfb4b008a8",
+    "main_vllm_commit": "856b15c62c8a574a1a0a289444d5b9a8120433e3",
     # vLLM tag for main branch
     "main_vllm_tag": "v0.19.1",
     # Python version for main branch

vllm_ascend/_310p/fused_moe/fused_moe.py

@@ -20,14 +20,11 @@
 from vllm.distributed import get_dp_group, get_ep_group, get_tp_group
 from vllm.model_executor.layers.fused_moe.config import FusedMoEConfig
 from vllm.model_executor.layers.fused_moe.layer import FusedMoE, UnquantizedFusedMoEMethod
-from vllm.model_executor.layers.fused_moe.shared_fused_moe import SharedFusedMoE
-
 from vllm_ascend.ascend_forward_context import _EXTRA_CTX, MoECommType
 from vllm_ascend.ops.fused_moe.experts_selector import zero_experts_compute
 from vllm_ascend.ops.fused_moe.moe_comm_method import FusedExpertsResult, _MoECommMethods
 from vllm_ascend.ops.fused_moe.moe_runtime_args import build_fused_experts_input
 from vllm_ascend.quantization.quant_type import QuantType
-from vllm_ascend.utils import vllm_version_is
 
 from .experts_selector import select_experts
 from .moe_comm_method import AllGatherCommImpl310
@@ -164,16 +161,14 @@ def __init__(self, *args, **kwargs):
 
         from vllm_ascend.ops.fused_moe.fused_moe import AscendMoERunner
 
-        is_legacy = vllm_version_is("0.19.1")
         self.runner = AscendMoERunner(
-            self if is_legacy else self.layer_name,
+            self.layer_name,
             self.moe_config,
             self.router,
-            self._routed_input_transform,
-            self.gate if is_legacy else kwargs.pop("gate", None),
-            self.shared_experts if is_legacy else kwargs.pop("shared_experts", None),
+            self.runner.routed_input_transform,
+            kwargs.pop("gate", None),
+            kwargs.pop("shared_experts", None),
             self.quant_method,
-            self.reduce_results,
             self.vllm_config.parallel_config.enable_dbo,
         )
 
@@ -263,7 +258,7 @@ def forward_impl(  # type: ignore[override]
         return routed_out
 
 
-class AscendSharedFusedMoE310(SharedFusedMoE, AscendFusedMoE310):
+class AscendSharedFusedMoE310(AscendFusedMoE310):
     def __init__(
         self,
         shared_experts: torch.nn.Module,
@@ -285,16 +280,14 @@ def __init__(
         # which at this point is still the stale runner built with shared_experts=None.
         from vllm_ascend.ops.fused_moe.fused_moe import AscendMoERunner
 
-        is_legacy = vllm_version_is("0.19.1")
         self.runner = AscendMoERunner(
-            self if is_legacy else self.layer_name,
+            self.layer_name,
             self.moe_config,
             self.router,
             self._routed_input_transform,
             self._gate,
             self._shared_experts,
             self.quant_method,
-            self.reduce_results,
             self.vllm_config.parallel_config.enable_dbo,
         )