[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/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