[Feat] Adapted mtp function to Qwen3-next (#3918)

### What this PR does / why we need it?

Adapts mtp function to Qwen3-next.

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

Signed-off-by: drslark <slarksblood@qq.com>

vllm_ascend/worker/model_runner_v1.py

@@ -1852,7 +1852,7 @@ class NPUModelRunner(LoRAModelRunnerMixin):
                         extra_attn_metadata_args = dict(
                             num_accepted_tokens=self.num_accepted_tokens.
                             gpu[:num_reqs],
-                            num_draft_tokens=self.num_draft_tokens.
+                            num_decode_draft_tokens_cpu=self.num_draft_tokens.
                             gpu[:num_reqs],
                         )
                     attn_metadata_i = builder.build(
@@ -1948,11 +1948,10 @@ class NPUModelRunner(LoRAModelRunnerMixin):
                 attn_state = AscendAttentionState.SpecDecoding
         # Speculative decoding.
         elif np.all(num_valid_tokens == 1):
-            if self.drafter and (self.drafter.name == SpecDcodeType.EAGLE
-                                 or self.drafter.name == SpecDcodeType.EAGLE3):
-                attn_state = AscendAttentionState.ChunkedPrefill
-            else:
+            if self.speculative_config and self.speculative_config.method == 'deepseek_mtp':
                 attn_state = AscendAttentionState.SpecDecoding
+            else:
+                attn_state = AscendAttentionState.ChunkedPrefill
         # splitfuse
         elif not ascend_config.ascend_scheduler_config.enabled or self.chunked_prefill_enabled:
             attn_state = AscendAttentionState.ChunkedPrefill
@@ -2548,7 +2547,7 @@ class NPUModelRunner(LoRAModelRunnerMixin):
         with ProfileExecuteDuration().capture_async("Draft"):
             if self.speculative_config:
                 use_padded_batch_for_eagle = self.speculative_config and \
-                    self.speculative_config.method == "deepseek_mtp" and \
+                    self.speculative_config.method in ("deepseek_mtp", "qwen3_next_mtp") and \
                     not self.speculative_config.disable_padded_drafter_batch
                 if use_padded_batch_for_eagle:
                     # EAGLE speculative decoding can use the GPU sampled tokens