[Bugfix][Model] Fix fusedmoe and make modelrunner_v1 compatible with latest vllm (#867)

### What this PR does / why we need it?
this PR fix CI failure broken by vllm.
1. add moe_config for fused_moe
2. adjust the change for kv cache group from vllm. currently vllm-ascend
doesn't support this feature. this is just a quick fix for backward
compatibility

fix: #872

---------

Signed-off-by: MengqingCao <cmq0113@163.com>

vllm_ascend/attention/mla_v1.py

@@ -16,6 +16,7 @@ from vllm.model_executor.layers.rotary_embedding import RotaryEmbedding
 
 from vllm_ascend.attention.attention_v1 import AscendAttentionState
 from vllm_ascend.ops.attention import vanilla_chunked_prefill_mla
+from vllm_ascend.utils import vllm_version_is
 from vllm_ascend.worker.model_runner_v1 import NPUModelRunner
 
 if TYPE_CHECKING:
@@ -238,8 +239,12 @@ class AscendMLAMetadataBuilder:
         # function. We should avoid GPU -> CPU sync as much as possible because
         # it blocks on all previous kernels.
         device = self.runner.device
-        block_table = (
-            self.runner.input_batch.block_table.get_device_tensor()[:num_reqs])
+        if vllm_version_is("0.8.5") or vllm_version_is("0.8.5.post1"):
+            block_table = (self.runner.input_batch.block_table.
+                           get_device_tensor()[:num_reqs])
+        else:
+            block_table = (self.runner.input_batch.block_table[0].
+                           get_device_tensor()[:num_reqs])
         slot_mapping = self.runner.slot_mapping_cpu[:num_actual_tokens].to(
             device, non_blocking=True)
         input_positions = self.runner.positions_cpu[:num_actual_tokens].to(
@@ -795,4 +800,4 @@ class AscendMLAImpl(MLAAttentionImpl):
                 output[:num_decode_tokens] = self._forward_decode(
                     decode_ql_nope, decode_q_pe, decode_k_nope, decode_k_pe,
                     kv_cache, attn_metadata)
-        return output_padded
+        return output_padded