[Main2Main] Upgrade vllm commit to 0123 (#6169)

### What this PR does / why we need it? 1. ✅ Upgrade vllm commit to: 0115 (8471b27df97c3eb79f891802fc0e858f8f7ac6a0) Modify import paths due to the refactors： https://github.com/vllm-project/vllm/pull/32245 https://github.com/vllm-project/vllm/pull/32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21034239336/job/60490156965?pr=5913 2. ✅Upgrade vllm commit to: 0119 (9a1f16da1e423ede2c2f52a9850cbfbb39cefe96) Fix `WorkerProc.__init__() missing 1 required positional argument: 'is_driver_worker'` due to https://github.com/vllm-project/vllm/pull/28506 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21156263050/job/60841668755?5569 3. ✅Upgrade vllm commit to: 0120(148117ea2e689cd43df4be6892671a17cdae5833) 1. Add `skip_compiled` param in `set_forward_context` due to https://github.com/vllm-project/vllm/pull/30385 2. Modify `tests/ut/spec_decode/test_eagle_proposer.py` due to https://github.com/vllm-project/vllm/pull/24322 change `self.max_num_tokens = vllm_config.scheduler_config.max_num_batched_tokens + max_batch_size` 3. Modify UT import paths due to the refactors：https://github.com/vllm-project/vllm/pull/32060 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21204851770/job/60999046946 4. ✅Upgrade vllm commit to: 0121(f23fb5a7c1b61350c5c40ca1115d3bf8cf2b8cc9) 1. vLLM switched `uses_mrope` from target to draft model config, making `positions`/`mrope_positions` mutually exclusive, breaking vllm-ascend's direct self.positions access and tests missing `draft_model_config.uses_mrope`. https://github.com/vllm-project/vllm/pull/32048 2. Moved bs_to_padded_graph_size from CompilationConfig to CudagraphDispatcher due to the refactor https://github.com/vllm-project/vllm/pull/30143 3. Remove unused `maybe_setup_kv_connector` due to https://github.com/vllm-project/vllm/pull/32077 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21217728738/job/61043738834 6. ✅Upgrade vllm commit to: 0122(8ebf271bb6d1e7e9b1a55be73d755ef1a57dbbe5) Updating FusedMoEParallelConfig (added enable_eplb) and FusedMoEConfig due to https://github.com/vllm-project/vllm/pull/32414 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21249922546/job/61148613054 8. ✅Upgrade vllm commit to: 0123(dc917cceb877dfd13f98c538c4c96158047d98bd) Setting temperature=0.0 due to the removal of the default temperature value in https://github.com/vllm-project/vllm/pull/32723 Test result: https://github.com/vllm-project/vllm-ascend/actions/runs/21280796875 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.14.0 - vLLM main: d68209402d --------- Signed-off-by: wjunLu <wjunlu217@gmail.com> Signed-off-by: Meihan-chen <jcccx.cmh@gmail.com> Co-authored-by: wjunLu <wjunlu217@gmail.com>
2026-01-27 08:44:36 +08:00
parent 9780a995e1
commit fea197ad50
25 changed files with 173 additions and 83 deletions
--- a/tests/ut/attention/test_mla_v1.py
+++ b/tests/ut/attention/test_mla_v1.py
@@ -17,6 +17,7 @@ from vllm_ascend.attention.mla_v1 import (AscendMLABackend,
                                          AscendMLAPrefillMetadata,
                                          ChunkedContextMetadata)
 from vllm_ascend.attention.utils import AscendCommonAttentionMetadata
+from vllm_ascend.utils import vllm_version_is


 class TestAscendMLABackend(TestBase):
@@ -223,7 +224,9 @@ class TestAscendMLAMetadataBuilder(TestBase):
            )

        self.parent_init_patcher = patch(
-            "vllm.v1.attention.backends.mla.common.MLACommonMetadataBuilder.__init__",
+            ("vllm.v1.attention.backends.mla.common.MLACommonMetadataBuilder.__init__"
+ if vllm_version_is('0.14.1') else
+ "vllm.model_executor.layers.attention.mla_attention.MLACommonMetadataBuilder.__init__"),
            mock_parent_init)
        self.parent_init_patcher.start()

@@ -449,7 +452,9 @@ class TestAscendMLAMetadataBuilderBuild(TestBase):
            )

        self.parent_init_patcher = patch(
-            "vllm.v1.attention.backends.mla.common.MLACommonMetadataBuilder.__init__",
+            ("vllm.v1.attention.backends.mla.common.MLACommonMetadataBuilder.__init__"
+ if vllm_version_is('0.14.1') else
+ "vllm.model_executor.layers.attention.mla_attention.MLACommonMetadataBuilder.__init__"),
            mock_parent_init)
        self.parent_init_patcher.start()

--- a/tests/ut/attention/test_sfa_v1.py
+++ b/tests/ut/attention/test_sfa_v1.py
@@ -13,7 +13,7 @@ if 'torch_npu._inductor' not in sys.modules:
 from vllm_ascend.attention.sfa_v1 import (AscendSFABackend, AscendSFAImpl,
                                          AscendSFAMetadata,
                                          AscendSFAMetadataBuilder)
-from vllm_ascend.utils import enable_dsa_cp
+from vllm_ascend.utils import enable_dsa_cp, vllm_version_is


 class TestAscendSFABackend(TestBase):
@@ -124,7 +124,9 @@ class TestAscendSFAMetadataBuilder(TestBase):
            )

        self.parent_init_patcher = patch(
-            "vllm.v1.attention.backends.mla.common.MLACommonMetadataBuilder.__init__",
+            ("vllm.v1.attention.backends.mla.common.MLACommonMetadataBuilder.__init__"
+ if vllm_version_is('0.14.1') else
+ "vllm.model_executor.layers.attention.mla_attention.MLACommonMetadataBuilder.__init__"),
            mock_parent_init)
        self.parent_init_patcher.start()

--- 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


@@ -20,8 +21,24 @@ class TestAscendConfig(unittest.TestCase):
            "refresh": True,
            "eplb_config": {"dynamic_eplb": True, "num_redundant_experts": 2},
        }
-        moe_parallel_config = FusedMoEParallelConfig(2, 0, 1, 2, 1, 1, 1, 1, True, "hccl")
-        moe_config = FusedMoEConfig(8, 8, 8192, 5, moe_parallel_config, torch.float16)
+        if vllm_version_is('0.14.1'):
+            moe_parallel_config = FusedMoEParallelConfig(2, 0, 1, 2, 1, 1, 1, 1, True, "hccl")
+            moe_config = FusedMoEConfig(8, 8, 8192, 5, moe_parallel_config, torch.float16)
+        else:
+            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)
+            moe_config = FusedMoEConfig(
+                num_experts=8,
+                experts_per_token=8,
+                hidden_dim=8192,
+                intermediate_size_per_partition=5,
+                num_local_experts=8,
+                activation="silu",
+                device="npu",
+                routing_method=RoutingMethodType.Simulated,
+                moe_parallel_config=moe_parallel_config,
+                in_dtype=torch.float16,
+            )
        moe_config.supports_eplb = True
        self.vllm_config = vllm_config
        self.moe_config = moe_config
--- a/tests/ut/spec_decode/test_eagle_proposer.py
+++ b/tests/ut/spec_decode/test_eagle_proposer.py
@@ -51,6 +51,7 @@ class TestEagleProposerInitialization(TestBase):
    def test_initialization_eagle_graph(self):
        self.vllm_config.speculative_config.method = "eagle"
        self.vllm_config.speculative_config.draft_model_config.get_hidden_size.return_value = 4096
+        self.vllm_config.speculative_config.draft_model_config.uses_mrope = False
        self.vllm_config.compilation_config.mode = CompilationMode.VLLM_COMPILE
        self.vllm_config.model_config.enforce_eager = False
        self.vllm_config.model_config.uses_mrope = False
@@ -65,10 +66,11 @@ class TestEagleProposerInitialization(TestBase):
        self.assertEqual(proposer.hidden_size, 4096)
        self.assertTrue(proposer.use_cuda_graph)

-        self.assertEqual(proposer.input_ids.shape, (1024, ))
-        self.assertEqual(proposer.positions.shape, (1024, ))
-        self.assertEqual(proposer.hidden_states.shape, (1024, 4096))
-        self.assertEqual(proposer.arange.shape, (1024, ))
+        expected_max_num_tokens = proposer.max_num_tokens
+        self.assertEqual(proposer.input_ids.shape, (expected_max_num_tokens, ))
+        self.assertEqual(proposer.positions.shape, (expected_max_num_tokens, ))
+        self.assertEqual(proposer.hidden_states.shape, (expected_max_num_tokens, 4096))
+        self.assertEqual(proposer.arange.shape, (expected_max_num_tokens, ))

    def test_initialization_eagle3_enforce_eager(self):
        self.vllm_config.speculative_config.method = "eagle3"
@@ -83,7 +85,8 @@ class TestEagleProposerInitialization(TestBase):

        self.assertEqual(proposer.hidden_size, 2048)
        self.assertFalse(proposer.use_cuda_graph)
-        self.assertEqual(proposer.hidden_states.shape, (1024, 2048))
+        expected_max_num_tokens = proposer.max_num_tokens
+        self.assertEqual(proposer.hidden_states.shape, (expected_max_num_tokens, 2048))

    def test_initialization_eagle3_full_graph_async(self):
        self.vllm_config.speculative_config.method = "eagle3"
@@ -100,7 +103,8 @@ class TestEagleProposerInitialization(TestBase):

        self.assertEqual(proposer.hidden_size, 2048)
        self.assertTrue(proposer.use_cuda_graph)
-        self.assertEqual(proposer.hidden_states.shape, (1024, 2048))
+        expected_max_num_tokens = proposer.max_num_tokens
+        self.assertEqual(proposer.hidden_states.shape, (expected_max_num_tokens, 2048))

    def test_initialization_mtp_full_graph_async(self):
        self.vllm_config.speculative_config.method = "mtp"
@@ -117,7 +121,8 @@ class TestEagleProposerInitialization(TestBase):

        self.assertEqual(proposer.hidden_size, 2048)
        self.assertFalse(proposer.use_cuda_graph)
-        self.assertEqual(proposer.hidden_states.shape, (1024, 2048))
+        expected_max_num_tokens = proposer.max_num_tokens
+        self.assertEqual(proposer.hidden_states.shape, (expected_max_num_tokens, 2048))


 class TestEagleProposerLoadModel(TestBase):
--- a/tests/ut/spec_decode/test_mtp_proposer.py
+++ b/tests/ut/spec_decode/test_mtp_proposer.py
@@ -33,6 +33,7 @@ class TestMtpProposer:
        config.speculative_config.method = "mtp"
        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.speculative_token_tree = str([
            (i + 1) * (0, ) for i in range(2)
        ])