bugfix for mtp>1 (#3174)

### What this PR does / why we need it?
fix bugs when mtp>1, and reorder input batch when mtp is not accepted.

### Does this PR introduce _any_ user-facing change?
no

### How was this patch tested?
by ci

- vLLM version: v0.10.2
- vLLM main:
52d0cb8458

---------

Signed-off-by: zouyida2052 <zouyida2002@gmail.com>

vllm_ascend/attention/mla_v1.py

@@ -202,6 +202,8 @@ class AscendMLAMetadataBuilder:
                 npu_fused_infer_attention_score TND layout's limit of 16, \
                 got {self.decode_threshold}"
 
+        self.reorder_batch_threshold = self.decode_threshold
+
         if self.chunked_prefill_enabled:
             self.chunked_prefill_workspace_size = min(
                 # Max sure there is enough for 8 full length request or at least

vllm_ascend/spec_decode/mtp_proposer.py

@@ -555,7 +555,7 @@ class MtpProposer(Proposer):
             # copy inputs to buffer for cudagraph
             self.input_ids[:batch_size] = input_ids
             self.positions[:batch_size] = clamped_positions
-            self.hidden_states[:batch_size] = hidden_states
+            self.hidden_states[:hidden_states.shape[0]] = hidden_states
             attn_metadata_i.slot_mapping[:batch_size] = slot_mapping
 
             if attn_metadata_i.prefill is not None: