[Core]Append padding logic for Attention (#3256)

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

This PR aims to add padding logic to seq_lens、block_tables when running
in full decode scenario. Before this PR, the number of input tokens with
padding might exceeds corresponding seq_lens. For example, when running
in full decode scenario:

```
input_ids : [1, 3, 0, 0]
seq_lens: [2, 1]
query_start_loc: [0, 1, 2]
```
Here, `input_ids` is padded by 2 tokens while
`seq_lens`/`query_start_loc` are not. The mismatch between `input_ids`
and `seq_lens`/`query_start_loc` might cause some potential bugs. This
PR would change it into :

```
input_ids : [1, 3, 0, 0]
seq_lens: [2, 1, 1, 1]
query_start_loc: [0, 1, 2, 3, 4]
```

### Does this PR introduce _any_ user-facing change?

No.

### How was this patch tested?


- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: Angazenn <supperccell@163.com>

vllm_ascend/worker/model_runner_v1.py

@@ -1477,6 +1477,7 @@ class NPUModelRunner(LoRAModelRunnerMixin):
                 seq_lens=self.seq_lens_cpu[:num_reqs],
                 num_reqs=num_reqs,
                 num_actual_tokens=total_num_scheduled_tokens,
+                num_input_tokens=num_input_tokens,
                 actual_seq_lengths_q=self.actual_seq_lengths_q,
                 # TODO: change this to the right block table for linear attn
                 block_table_tensor=blk_table_tensor[:num_reqs],
@@ -1523,8 +1524,6 @@ class NPUModelRunner(LoRAModelRunnerMixin):
                         model=self.get_model(),
                         **extra_attn_metadata_args)
 
-                if self.vllm_config.model_config.use_mla or self.use_sparse:
-                    attn_metadata_i.num_input_tokens = num_input_tokens
                 for layer_name in attn_group.layer_names:
                     attn_metadata[layer_name] = attn_metadata_i