[main2main]upgrade main to 0214

.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: "v0.15.0"
+        default: "v0.16.0"
         type: string
         description: vllm version to use
       vllm_ascend_remote_url:

.github/workflows/bot_pr_create.yaml

@@ -37,7 +37,7 @@ jobs:
     steps:
       - name: Get vLLM version
         run: |
-          VLLM_COMMIT=83b47f67b1dfad505606070ae4d9f83e50ad4ebd
+          VLLM_COMMIT=b3c14229b032a8bbf93d450a52c9a404ddaea429
           echo "VLLM_COMMIT=https://github.com/vllm-project/vllm/commit/$VLLM_COMMIT" >> "$GITHUB_ENV"
 
       - name: Checkout repository

.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=83b47f67b1dfad505606070ae4d9f83e50ad4ebd
+ARG VLLM_COMMIT=b3c14229b032a8bbf93d450a52c9a404ddaea429
 RUN git clone $VLLM_REPO /vllm-workspace/vllm && \
     cd /vllm-workspace/vllm && \
     git checkout $VLLM_COMMIT

.github/workflows/pr_test_full.yaml

@@ -75,7 +75,7 @@ jobs:
     name: e2e-full
     strategy:
       matrix:
-        vllm_version: [83b47f67b1dfad505606070ae4d9f83e50ad4ebd, v0.15.0]
+        vllm_version: [b3c14229b032a8bbf93d450a52c9a404ddaea429, v0.16.0]
     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: 83b47f67b1dfad505606070ae4d9f83e50ad4ebd
+      vllm: b3c14229b032a8bbf93d450a52c9a404ddaea429
   changes:
     runs-on: linux-aarch64-a2b3-0
     outputs:
@@ -87,7 +87,7 @@ jobs:
     if: ${{ needs.lint.result == 'success' && (needs.changes.outputs.e2e_tracker == 'true' || needs.changes.outputs.ut_tracker == 'true') }}
     strategy:
       matrix:
-        vllm_version: [83b47f67b1dfad505606070ae4d9f83e50ad4ebd, v0.15.0]
+        vllm_version: [b3c14229b032a8bbf93d450a52c9a404ddaea429, v0.16.0]
     uses: ./.github/workflows/_unit_test.yaml
     with:
       vllm: ${{ matrix.vllm_version }}
@@ -99,7 +99,7 @@ jobs:
     name: e2e-light
     strategy:
       matrix:
-        vllm_version: [83b47f67b1dfad505606070ae4d9f83e50ad4ebd, v0.15.0]
+        vllm_version: [b3c14229b032a8bbf93d450a52c9a404ddaea429, v0.16.0]
     # 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.

.github/workflows/schedule_codecov_refresh.yaml

@@ -33,7 +33,7 @@ jobs:
     name: refresh codecov
     strategy:
       matrix:
-        vllm_version: [83b47f67b1dfad505606070ae4d9f83e50ad4ebd]
+        vllm_version: [b3c14229b032a8bbf93d450a52c9a404ddaea429]
     uses: ./.github/workflows/_unit_test.yaml
     with:
       vllm: ${{ matrix.vllm_version }}

.github/workflows/schedule_nightly_test_a2.yaml

@@ -133,7 +133,7 @@ jobs:
               - Qwen3-Omni-30B-A3B-Instruct
     uses: ./.github/workflows/_e2e_nightly_single_node_models.yaml
     with:
-      vllm: v0.15.0
+      vllm: v0.16.0
       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'

.github/workflows/schedule_test_benchmarks.yaml

@@ -51,7 +51,7 @@ jobs:
     strategy:
       matrix:
         include:
-          - vllm_branch: v0.15.0
+          - vllm_branch: v0.16.0
             vllm_ascend_branch: main
       max-parallel: 1
     container:

Dockerfile

@@ -50,7 +50,7 @@ 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=v0.15.0
+ARG VLLM_TAG=v0.16.0
 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/ && \

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=v0.15.0
+ARG VLLM_TAG=v0.16.0
 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/ && \

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=v0.15.0
+ARG VLLM_TAG=v0.16.0
 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/ && \

Dockerfile.a3

@@ -49,7 +49,7 @@ RUN apt-get update -y && \
 
 # Install vLLM
 ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
-ARG VLLM_TAG=v0.15.0
+ARG VLLM_TAG=v0.16.0
 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/ && \

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=v0.15.0
+ARG VLLM_TAG=v0.16.0
 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/ && \

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=v0.15.0
+ARG VLLM_TAG=v0.16.0
 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/ && \

docs/source/community/versioning_policy.md

@@ -56,7 +56,7 @@ 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    | 83b47f67b1dfad505606070ae4d9f83e50ad4ebd, v0.15.0 tag | >= 3.10, < 3.12   | 8.5.0 | 2.9.0 / 2.9.0 |
+|     main    | b3c14229b032a8bbf93d450a52c9a404ddaea429, v0.16.0 tag | >= 3.10, < 3.12   | 8.5.0 | 2.9.0 / 2.9.0 |
 
 ## Release cadence
 

docs/source/conf.py

@@ -77,7 +77,7 @@
     # CANN image tag
     "cann_image_tag": "8.5.0-910b-ubuntu22.04-py3.11",
     # vllm version in ci
-    "ci_vllm_version": "v0.15.0",
+    "ci_vllm_version": "v0.16.0",
 }
 
 # For cross-file header anchors

tests/e2e/singlecard/compile/backend.py

@@ -20,15 +20,10 @@
 
 import torch.fx as fx
 from torch._inductor.decomposition import select_decomp_table
+from vllm.compilation.passes.fx_utils import OpOverload
 from vllm.config import get_current_vllm_config
 
 from vllm_ascend.compilation.compiler_interface import compile_fx
-from vllm_ascend.utils import vllm_version_is
-
-if vllm_version_is("0.15.0"):
-    from vllm.compilation.fx_utils import OpOverload  # type: ignore
-else:
-    from vllm.compilation.passes.fx_utils import OpOverload
 
 
 class TestBackend:

tests/e2e/singlecard/compile/test_norm_quant_fusion.py

@@ -19,6 +19,7 @@
 import torch
 import torch.nn as nn
 import vllm.config
+from vllm.compilation.passes.fx_utils import OpOverload
 from vllm.config import ModelConfig, VllmConfig
 from vllm.distributed import ensure_model_parallel_initialized, init_distributed_environment
 from vllm.utils.system_utils import update_environment_variables
@@ -27,13 +28,7 @@
 from tests.e2e.singlecard.compile.backend import TestBackend
 from vllm_ascend.ascend_forward_context import set_ascend_forward_context
 from vllm_ascend.compilation.passes.norm_quant_fusion_pass import AddRMSNormQuantFusionPass
-from vllm_ascend.utils import enable_custom_op, vllm_version_is
-
-if vllm_version_is("0.15.0"):
-    from vllm.compilation.fx_utils import OpOverload  # type: ignore
-else:
-    from vllm.compilation.passes.fx_utils import OpOverload
-
+from vllm_ascend.utils import enable_custom_op
 
 # Cache backend to avoid duplicate pattern registration
 _backend_cache = None

tests/ut/eplb/core/test_eplb_utils.py

@@ -22,9 +22,9 @@ def setUp(self, mock_fix_incompatible_config):
             "eplb_config": {"dynamic_eplb": True, "num_redundant_experts": 2},
         }
         from vllm.model_executor.layers.fused_moe.config import RoutingMethodType
-        if vllm_version_is("0.15.0"):
+        if vllm_version_is("0.16.0"):
             moe_parallel_config = FusedMoEParallelConfig(
-                2, 0, 1, 2, 1, 1, 1, 1, True, "hccl", enable_eplb=True)
+                2, 0, 1, 2, 1, 1, 1, 1, True, "hccl", is_sequence_parallel=True, enable_eplb=True)
             moe_config = FusedMoEConfig(
                 num_experts=8,
                 experts_per_token=8,

tests/ut/quantization/test_modelslim_config.py

@@ -9,10 +9,7 @@
 from vllm_ascend.quantization.modelslim_config import AscendModelSlimConfig
 from vllm_ascend.utils import ASCEND_QUANTIZATION_METHOD, vllm_version_is
 
-if vllm_version_is("v0.15.0"):
-    from vllm.attention.layer import Attention  # type: ignore
-else:
-    from vllm.model_executor.layers.attention import Attention
+from vllm.model_executor.layers.attention import Attention
 
 
 class TestAscendModelSlimConfig(TestBase):

vllm_ascend/ascend_forward_context.py

@@ -19,7 +19,6 @@
     is_drafter_moe_model,
     is_moe_model,
     speculative_enable_dispatch_gmm_combine_decode,
-    vllm_version_is,
 )
 
 
@@ -152,10 +151,6 @@ def set_ascend_forward_context(
                 mc2_mask[:num_actual_tokens] = True
                 mc2_mask[num_actual_tokens:] = False
                 forward_context.mc2_mask = mc2_mask
-
-        if is_draft_model and vllm_version_is("0.15.0"):
-            forward_context.remaining_moe_layers = None
-
         try:
             yield
         finally:

vllm_ascend/compilation/graph_fusion_pass_manager.py

@@ -17,17 +17,10 @@
 #
 
 from torch import fx as fx
+from vllm.compilation.passes.inductor_pass import get_pass_context
+from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
 from vllm.config import VllmConfig
 
-from vllm_ascend.utils import vllm_version_is
-
-if vllm_version_is("0.15.0"):
-    from vllm.compilation.inductor_pass import get_pass_context  # type: ignore
-    from vllm.compilation.vllm_inductor_pass import VllmInductorPass  # type: ignore
-else:
-    from vllm.compilation.passes.inductor_pass import get_pass_context
-    from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
-
 
 class GraphFusionPassManager:
     """

vllm_ascend/compilation/passes/allreduce_rmsnorm_fusion_pass.py

@@ -16,6 +16,8 @@
 #
 import torch
 from torch._inductor.pattern_matcher import Match, PatternMatcherPass, PatternPrettyPrinter
+from vllm.compilation.passes.inductor_pass import get_pass_context
+from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
 from vllm.config import VllmConfig
 from vllm.config.compilation import Range
 from vllm.distributed import get_tensor_model_parallel_world_size, tensor_model_parallel_all_reduce
@@ -24,14 +26,6 @@
 
 from vllm_ascend.compilation.passes.base_pattern import BasePattern
 from vllm_ascend.compilation.passes.utils.npugraph_ex_utils_check import extra_stream_scope_check
-from vllm_ascend.utils import vllm_version_is
-
-if vllm_version_is("0.15.0"):
-    from vllm.compilation.inductor_pass import get_pass_context  # type: ignore
-    from vllm.compilation.vllm_inductor_pass import VllmInductorPass  # type: ignore
-else:
-    from vllm.compilation.passes.inductor_pass import get_pass_context
-    from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
 
 # computation-communication tiling block is 512
 ALLREDUCE_NORM_FUSE_THRESHOLD = 512

vllm_ascend/compilation/passes/norm_quant_fusion_pass.py

@@ -17,17 +17,13 @@
 #
 import torch
 from torch._inductor.pattern_matcher import PatternMatcherPass
+from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
 from vllm.config import VllmConfig
 from vllm.config.compilation import Range
 from vllm.logger import logger
 
 from vllm_ascend.compilation.passes.base_pattern import BasePattern
-from vllm_ascend.utils import enable_custom_op, vllm_version_is
-
-if vllm_version_is("0.15.0"):
-    from vllm.compilation.vllm_inductor_pass import VllmInductorPass  # type: ignore
-else:
-    from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
+from vllm_ascend.utils import enable_custom_op
 
 
 class AddRMSNormQuantPattern(BasePattern):

vllm_ascend/compilation/passes/qknorm_rope_fusion_pass.py

@@ -17,19 +17,13 @@
 #
 import torch
 from torch._inductor.pattern_matcher import PatternMatcherPass, PatternPrettyPrinter
+from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
 from vllm.config import VllmConfig, get_layers_from_vllm_config
 from vllm.config.compilation import Range
 from vllm.logger import logger
+from vllm.model_executor.layers.attention import Attention
 
 from vllm_ascend.compilation.passes.base_pattern import BasePattern
-from vllm_ascend.utils import vllm_version_is
-
-if vllm_version_is("v0.15.0"):
-    from vllm.attention.layer import Attention  # type: ignore
-    from vllm.compilation.vllm_inductor_pass import VllmInductorPass  # type: ignore
-else:
-    from vllm.compilation.passes.vllm_inductor_pass import VllmInductorPass
-    from vllm.model_executor.layers.attention import Attention
 
 
 class QKNormRopeFusionPattern(BasePattern):

vllm_ascend/distributed/kv_transfer/kv_pool/cpu_offload/cpu_offload_connector.py

@@ -26,7 +26,6 @@
     MetadataServerProc,
     MLAConfig,
 )
-from vllm_ascend.utils import vllm_version_is
 
 if TYPE_CHECKING:
     from vllm.forward_context import ForwardContext
@@ -35,10 +34,7 @@
     from vllm.v1.kv_cache_interface import KVCacheConfig
     from vllm.v1.request import Request
 
-if vllm_version_is("v0.15.0"):
-    from vllm.attention.layer import Attention, MLAAttention  # type: ignore
-else:
-    from vllm.model_executor.layers.attention import Attention, MLAAttention
+from vllm.model_executor.layers.attention import Attention, MLAAttention
 
 
 @dataclass