[CORE]initial support for torchair with non-mla backend (#1506)

### What this PR does / why we need it?
This PR supports torchair graph mode with non-mla backend on both 800IA2
and 300I Duo platforms. The main change is to add
`attention_v1_torchair.py` to support specific attention related
operations that are required by torchair.

### Does this PR introduce _any_ user-facing change?
Before this PR, vLLM-Ascend only allows deepseek to use torchair. Now we
can also use it with pangu. Besides, we add a support model list to
control which type of models that can use torchair.

### How was this patch tested?
We have test it with PanguProMoE on both 800IA2 and 300I Duo platforms,
and model generates answer normally.

---------

Signed-off-by: angazenn <zengyanjia@huawei.com>
Signed-off-by: tianyitang <tangtianyi4@huawei.com>
Co-authored-by: angazenn <zengyanjia@huawei.com>
Co-authored-by: tianyitang <tangtianyi4@huawei.com>

vllm_ascend/quantization/w8a8.py

@@ -406,10 +406,12 @@ class AscendC8KVCacheMethod:
                                       "implemented for "
                                       "PrefillCacheHit")
         elif attn_metadata.attn_state == AscendAttentionState.DecodeOnly:  # changed attn_metadata.attn_state == AscendAttentionState.DecodeOnly
-            # torch_air
-            # decode_meta = attn_metadata.decode
-            # seq_lens = decode_meta.seq_lens_list
-            seq_lens = attn_metadata.seq_lens
+            if hasattr(attn_metadata, "decode"):
+                # torch_air
+                decode_meta = attn_metadata.decode
+                seq_lens = decode_meta.seq_lens_list
+            else:
+                seq_lens = attn_metadata.seq_lens
             block_size = key_cache.shape[1]
             query = query.view(num_tokens, 1, layer.num_heads *
                                layer.head_size).contiguous()  # changed