[Bugfix] Fix MTP support for lmhead_tensor_parallel_size (#3915)

### What this PR does / why we need it?
Fix the issue of MTP being enabled and setting
Imhead_tensor_parallel_size=16 causing the inference to hang.

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

Signed-off-by: wyh145 <1987244901@qq.com>

vllm_ascend/worker/model_runner_v1.py

@@ -2913,7 +2913,8 @@ class NPUModelRunner(LoRAModelRunnerMixin):
                     aclgraph_runtime_mode=aclgraph_runtime_mode,
                     batch_descriptor=batch_descriptor)
                 if need_dummy_logits:
-                    dummy_compute_logits(hidden_states)
+                    self.drafter.model.compute_logits(
+                        hidden_states[dummy_indices])
             if self.in_profile_run and self.dynamic_eplb:
                 self.model.clear_all_moe_loads()
             if not self.in_profile_run and self.dynamic_eplb: