Enable kvcache_nz for the decode process in torchair graph mode (#1098)

What this PR does / why we need it?
Enable kvcache_nz for the decode process in torchair graph mode, which
reduces the time consumed by FA in long sequences.

Does this PR introduce any user-facing change?
If need to enable kvcache_nz, should set the
additional_config.torchair_graph_config.enable_kv_nz=True

How was this patch tested?
1. Tested in deepseek model:
with batchsize 64 and seq_len 1k+3k, 61 layers FA total time improves
20.80ms -> 19.76ms
2. operator precision test: 

[aclnnFusedInferAttentionScoreV3_result.csv](https://github.com/user-attachments/files/20664138/aclnnFusedInferAttentionScoreV3_result.csv)
3. tpot test from @ttanzhiqiang, and curl one result is normal

https://github.com/vllm-project/vllm-ascend/pull/1098#issuecomment-2948542159

https://github.com/vllm-project/vllm-ascend/pull/1098#issuecomment-2954496588

---------

Signed-off-by: chenwaner <861645847@qq.com>

docs/source/user_guide/additional_config.md

@@ -44,6 +44,7 @@ The details of each config option are as follows:
 | `use_cached_graph` | bool | `False` | Whether to use cached graph |
 | `graph_batch_sizes` | list[int] | `[]` | The batch size for torchair graph cache |
 | `graph_batch_sizes_init` | bool | `False` | Init graph batch size dynamically if `graph_batch_sizes` is empty |
+| `enable_kv_nz`| bool | `False` | Whether to enable kvcache NZ layout |
 
 **ascend_scheduler_config**
 
@@ -64,7 +65,8 @@ A full example of additional configuration is as follows:
         "use_cached_graph": true,
         "graph_batch_sizes": [1, 2, 4, 8],
         "graph_batch_sizes_init": false,
-        "enable_multistream_moe": false
+        "enable_multistream_moe": false,
+        "enable_kv_nz": false
     },
     "ascend_scheduler_config": {
         "enabled": true,