[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/attention/utils.py

@@ -64,6 +64,10 @@ class AscendCommonAttentionMetadata:
 
     graph_pad_size: int = -1
 
+    # num_input_tokens refers to total number of tokens including
+    # padding tokens. It is used to handle some padding operations.
+    num_input_tokens: int = 0
+
     # NOTE: This is a temporary solution for rotary embedding in MLA
     cos: torch.Tensor = None
     sin: torch.Tensor = None