[main2main] upgrade vllm main 0202 (#6560)

### What this PR does / why we need it? 1. Fix `TypeError: FusedMoEParallelConfig.__init__() missing 1 required positional argument: 'is_sequence_parallel'` due to https://github.com/vllm-project/vllm/pull/32567 2. Fix ` TypeError: '>' not supported between instances of 'MagicMock' and 'int'` due to https://github.com/vllm-project/vllm/pull/33035 3. Fix `TypeError: Can't instantiate abstract class AscendMLAImpl with abstract methods forward_mha, forward_mqa` and AttributeError: 'bool' object has no attribute 'process_weights_after_loading' due to https://github.com/vllm-project/vllm/pull/33284 4. Fix `'AscendSharedFusedMoE' object has no attribute '_routed_input_transform'`due to https://github.com/vllm-project/vllm/pull/32790 5. Fix `NPUModelRunner._dummy_run() got an unexpected keyword argument 'num_active_loras'` due to https://github.com/vllm-project/vllm/pull/32005 6. Fix the problem caused by` 'tuple' object has no attribute 'job_id'` due to https://github.com/vllm-project/vllm/pull/27492 7. Fix the problem that all_moe_layers is not equal to vllm.moe_forward, vllm.moe_forward_shared due to https://github.com/vllm-project/vllm/pull/33184 8. Add patch to fix the problem "got multiple values for keyword argument 'add_special_tokens'" due to https://github.com/vllm-project/vllm/pull/32863 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.15.0 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.15.0 --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com>
2026-02-05 19:31:17 +08:00
parent 2c1608265b
commit 922e5c163b
28 changed files with 246 additions and 30 deletions
--- a/tests/e2e/conftest.py
+++ b/tests/e2e/conftest.py
@@ -922,4 +922,7 @@ PROMPT_CONFIGS = {

@pytest.fixture(params=PROMPT_CONFIGS.keys())
 def vl_config(request):
-    return PROMPT_CONFIGS[request.param]
+    config = PROMPT_CONFIGS[request.param]
+    if "skip" in config:
+        pytest.skip(config["skip"])
+    return config
--- a/tests/ut/eplb/core/test_eplb_utils.py
+++ b/tests/ut/eplb/core/test_eplb_utils.py
@@ -9,6 +9,7 @@ from vllm.model_executor.layers.fused_moe.config import FusedMoEConfig, FusedMoE

 from vllm_ascend.ascend_config import init_ascend_config
 from vllm_ascend.eplb.core.eplb_utils import init_eplb_config
+from vllm_ascend.utils import vllm_version_is
 # isort: on


@@ -21,7 +22,13 @@ class TestAscendConfig(unittest.TestCase):
            "eplb_config": {"dynamic_eplb": True, "num_redundant_experts": 2},
        }
        from vllm.model_executor.layers.fused_moe.config import RoutingMethodType
-        moe_parallel_config = FusedMoEParallelConfig(2, 0, 1, 2, 1, 1, 1, 1, True, "hccl", enable_eplb=True)
+        if vllm_version_is("0.15.0"):
+            moe_parallel_config = FusedMoEParallelConfig(
+                2, 0, 1, 2, 1, 1, 1, 1, True, "hccl", enable_eplb=True)
+        else:
+            moe_parallel_config = FusedMoEParallelConfig(
+                2, 0, 1, 2, 1, 1, 1, 1, True, "hccl",
+                is_sequence_parallel=False, enable_eplb=True)
        moe_config = FusedMoEConfig(
            num_experts=8,
            experts_per_token=8,
--- a/tests/ut/ops/test_mla.py
+++ b/tests/ut/ops/test_mla.py
@@ -82,8 +82,13 @@ class TestAscendMultiHeadLatentAttention(TestBase):
    @patch("vllm_ascend.ops.mla.get_tensor_model_parallel_world_size")
    def test_initialization(self, mock_tp_size, mock_ascend_config,
                            mock_get_vllm_config):
+        # Create a proper mock for MLAAttention that has the required attributes
+        mock_mla_attn = MagicMock()
+        mock_mla_attn.process_weights_after_loading = MagicMock()
+        mock_mla_attn.impl = MagicMock()
+        mock_mla_attn.impl.process_weights_after_loading = MagicMock()

-        with patch("vllm_ascend.ops.mla.MLAAttention", return_value=True):
+        with patch("vllm_ascend.ops.mla.MLAAttention", return_value=mock_mla_attn):
            mock_tp_size.return_value = 2
            mock_ascend_config.return_value.enable_shared_expert_dp = True
            mock_vllm_config = MagicMock(spec=VllmConfig)
@@ -126,7 +131,14 @@ class TestAscendMultiHeadLatentAttention(TestBase):
            num_hidden_layers=32, first_k_dense_replace=False)
        mock_get_vllm_config.return_value = mock_vllm_config
        mock_vllm_config.compilation_config = CompilationConfig()
-        with patch("vllm_ascend.ops.mla.MLAAttention", return_value=True):
+
+        # Create a proper mock for MLAAttention that has the required attributes
+        mock_mla_attn = MagicMock()
+        mock_mla_attn.process_weights_after_loading = MagicMock()
+        mock_mla_attn.impl = MagicMock()
+        mock_mla_attn.impl.process_weights_after_loading = MagicMock()
+
+        with patch("vllm_ascend.ops.mla.MLAAttention", return_value=mock_mla_attn):
            attn = AscendMultiHeadLatentAttention(
                hidden_size=self.hidden_size,
                num_heads=self.num_heads,
--- a/tests/ut/quantization/test_modelslim_config.py
+++ b/tests/ut/quantization/test_modelslim_config.py
@@ -1,6 +1,5 @@
 from unittest.mock import MagicMock, patch

-from vllm.attention.layer import Attention
 from vllm.model_executor.layers.fused_moe import FusedMoE
 from vllm.model_executor.layers.fused_moe.config import FusedMoEConfig
 from vllm.model_executor.layers.linear import LinearBase
@@ -8,7 +7,12 @@ from vllm.model_executor.layers.linear import LinearBase
 from tests.ut.base import TestBase
 from vllm_ascend.ops.linear import AscendUnquantizedLinearMethod
 from vllm_ascend.quantization.modelslim_config import AscendModelSlimConfig
-from vllm_ascend.utils import ASCEND_QUANTIZATION_METHOD
+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


 class TestAscendModelSlimConfig(TestBase):
--- a/tests/ut/spec_decode/test_eagle_proposer.py
+++ b/tests/ut/spec_decode/test_eagle_proposer.py
@@ -28,12 +28,15 @@ class TestEagleProposerInitialization(TestBase):
        self.vllm_config.model_config.dtype = torch.float16
        self.vllm_config.model_config.max_model_len = 2048
        self.vllm_config.model_config.uses_mrope = False
+        self.vllm_config.model_config.uses_xdrope_dim = 0
        self.vllm_config.parallel_config.tensor_parallel_size = 1
+        self.vllm_config.parallel_config.data_parallel_rank = 0
        self.vllm_config.speculative_config.draft_tensor_parallel_size = 1
        self.vllm_config.speculative_config.num_speculative_tokens = 2
        self.vllm_config.speculative_config.speculative_token_tree = str([
            (i + 1) * (0, ) for i in range(2)
        ])
+        self.vllm_config.speculative_config.draft_model_config.uses_xdrope_dim = 0
        self.vllm_config.additional_config = None

        self.mock_cpugpubuffer = patch(
@@ -141,12 +144,15 @@ class TestEagleProposerLoadModel(TestBase):
        self.vllm_config.model_config.dtype = torch.float16
        self.vllm_config.model_config.max_model_len = 2048
        self.vllm_config.model_config.uses_mrope = False
+        self.vllm_config.model_config.uses_xdrope_dim = 0
        self.vllm_config.parallel_config.tensor_parallel_size = 1
+        self.vllm_config.parallel_config.data_parallel_rank = 0
        self.vllm_config.speculative_config.draft_tensor_parallel_size = 1
        self.vllm_config.speculative_config.num_speculative_tokens = 2
        self.vllm_config.speculative_config.speculative_token_tree = str([
            (i + 1) * (0, ) for i in range(2)
        ])
+        self.vllm_config.speculative_config.draft_model_config.uses_xdrope_dim = 0
        self.vllm_config.additional_config = None
        init_ascend_config(self.vllm_config)

@@ -285,12 +291,15 @@ class TestEagleProposerDummyRun(TestBase):
        self.vllm_config.model_config.dtype = torch.float16
        self.vllm_config.model_config.max_model_len = 2048
        self.vllm_config.model_config.uses_mrope = False
+        self.vllm_config.model_config.uses_xdrope_dim = 0
        self.vllm_config.model_config.use_mla = False
        self.vllm_config.parallel_config.tensor_parallel_size = 1
+        self.vllm_config.parallel_config.data_parallel_rank = 0
        self.vllm_config.speculative_config.draft_tensor_parallel_size = 1
        self.vllm_config.speculative_config.speculative_token_tree = str([
            (i + 1) * (0, ) for i in range(4)
        ])
+        self.vllm_config.speculative_config.draft_model_config.uses_xdrope_dim = 0
        self.vllm_config.additional_config = None
        init_ascend_config(self.vllm_config)

@@ -404,12 +413,15 @@ class TestEagleProposerHelperMethods(TestBase):
        self.vllm_config.model_config.dtype = torch.float16
        self.vllm_config.model_config.max_model_len = 2048
        self.vllm_config.model_config.uses_mrope = False
+        self.vllm_config.model_config.uses_xdrope_dim = 0
        self.vllm_config.parallel_config.tensor_parallel_size = 1
+        self.vllm_config.parallel_config.data_parallel_rank = 0
        self.vllm_config.speculative_config.draft_tensor_parallel_size = 1
        self.vllm_config.speculative_config.num_speculative_tokens = 2
        self.vllm_config.speculative_config.speculative_token_tree = str([
            (i + 1) * (0, ) for i in range(2)
        ])
+        self.vllm_config.speculative_config.draft_model_config.uses_xdrope_dim = 0
        self.vllm_config.additional_config = None
        init_ascend_config(self.vllm_config)

--- a/tests/ut/spec_decode/test_mtp_proposer.py
+++ b/tests/ut/spec_decode/test_mtp_proposer.py
@@ -34,6 +34,7 @@ class TestMtpProposer:
        config.speculative_config.draft_model_config = MagicMock()
        config.speculative_config.draft_model_config.get_hidden_size.return_value = 4096
        config.speculative_config.draft_model_config.uses_mrope = False
+        config.speculative_config.draft_model_config.uses_xdrope_dim = 0
        config.speculative_config.speculative_token_tree = str([
            (i + 1) * (0, ) for i in range(2)
        ])
@@ -42,9 +43,11 @@ class TestMtpProposer:
        config.model_config.dtype = torch.float16
        config.model_config.max_model_len = 2048
        config.model_config.uses_mrope = False
+        config.model_config.uses_xdrope_dim = 0
        config.model_config.hf_text_config = None
        config.model_config.hf_config = None
        config.parallel_config.tensor_parallel_size = 1
+        config.parallel_config.data_parallel_rank = 0
        config.speculative_config.draft_tensor_parallel_size = 1

        config.load_config = None