[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

### What this PR does / why we need it?
This is the step 1 of refactoring code to adapt with vllm main, and this
pr aligned with
17c540a993

1. refactor deepseek to the latest code arch as of
17c540a993
 
2. bunches of fixes due to vllm changes
- Fix `AscendScheduler` `__post_init__`, caused by
https://github.com/vllm-project/vllm/pull/25075
- Fix `AscendScheduler` init got an unexpected arg `block_size`, caused
by https://github.com/vllm-project/vllm/pull/26296
- Fix `KVCacheManager` `get_num_common_prefix_blocks` arg, caused by
https://github.com/vllm-project/vllm/pull/23485
- Fix `MLAAttention` import,caused by
https://github.com/vllm-project/vllm/pull/25103
- Fix `SharedFusedMoE` import, caused by
https://github.com/vllm-project/vllm/pull/26145
- Fix `LazyLoader` improt, caused by
https://github.com/vllm-project/vllm/pull/27022
- Fix `vllm.utils.swap_dict_values` improt, caused by
https://github.com/vllm-project/vllm/pull/26990
- Fix `Backend` enum import, caused by
https://github.com/vllm-project/vllm/pull/25893
- Fix `CompilationLevel` renaming to `CompilationMode` issue introduced
by https://github.com/vllm-project/vllm/pull/26355
- Fix fused_moe ops, caused by
https://github.com/vllm-project/vllm/pull/24097
- Fix bert model because of `inputs_embeds`, caused by
https://github.com/vllm-project/vllm/pull/25922
- Fix MRope because of `get_input_positions_tensor` to
`get_mrope_input_positions`, caused by
https://github.com/vllm-project/vllm/pull/24172
- Fix `splitting_ops` changes introduced by
https://github.com/vllm-project/vllm/pull/25845
- Fix multi-modality changes introduced by
https://github.com/vllm-project/vllm/issues/16229
- Fix lora bias dropping issue introduced by
https://github.com/vllm-project/vllm/pull/25807
- Fix structured ouput break introduced by
https://github.com/vllm-project/vllm/issues/26737

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

### How was this patch tested?
CI passed with existing test.


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

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
Signed-off-by: Icey <1790571317@qq.com>
Co-authored-by: Icey <1790571317@qq.com>

vllm_ascend/ops/common_fused_moe.py

@@ -19,7 +19,7 @@ from typing import Any, Callable, Optional
 
 import torch
 import torch_npu
-from vllm.config import CompilationLevel, get_current_vllm_config
+from vllm.config import get_current_vllm_config
 from vllm.distributed import (get_dp_group, get_ep_group, get_tp_group,
                               tensor_model_parallel_all_reduce)
 from vllm.forward_context import get_forward_context
@@ -28,7 +28,6 @@ from vllm.model_executor.layers.fused_moe.config import FusedMoEConfig
 from vllm.model_executor.layers.fused_moe.layer import (
     FusedMoE, UnquantizedFusedMoEMethod, determine_expert_map,
     get_compressed_expert_map)
-from vllm.model_executor.layers.shared_fused_moe import SharedFusedMoE
 
 from vllm_ascend.ascend_config import get_ascend_config
 from vllm_ascend.ascend_forward_context import MoECommType
@@ -41,7 +40,17 @@ from vllm_ascend.ops.moe.moe_comm_method import setup_moe_comm_method
 from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_NZ, enable_sp, is_310p,
                                is_enable_nz, npu_stream_switch,
                                shared_expert_dp_enabled,
-                               shared_experts_calculation_stream)
+                               shared_experts_calculation_stream,
+                               vllm_version_is)
+
+if vllm_version_is("0.11.0"):
+    from vllm.config import CompilationLevel
+
+    from vllm.model_executor.layers.shared_fused_moe import SharedFusedMoE  # type: ignore # isort:skip
+else:
+    from vllm.config import CompilationMode
+    from vllm.model_executor.layers.fused_moe.shared_fused_moe import \
+        SharedFusedMoE
 
 
 class AscendUnquantizedFusedMoEMethod(UnquantizedFusedMoEMethod):
@@ -60,9 +69,17 @@ class AscendUnquantizedFusedMoEMethod(UnquantizedFusedMoEMethod):
         if ascend_config.torchair_graph_config.enabled:
             self.use_aclgraph = False
         else:
-            self.use_aclgraph = (vllm_config.compilation_config.level
-                                 == CompilationLevel.PIECEWISE and
-                                 not vllm_config.model_config.enforce_eager)
+            if vllm_version_is("0.11.0"):
+                self.use_aclgraph = (
+                    vllm_config.compilation_config.level
+                    == CompilationLevel.PIECEWISE
+                    and not vllm_config.model_config.enforce_eager)
+            else:
+                self.use_aclgraph = (
+                    vllm_config.compilation_config.mode
+                    == CompilationMode.VLLM_COMPILE
+                    and not vllm_config.model_config.enforce_eager)
+
         self.transpose = True
 
     def process_weights_after_loading(self, layer):
@@ -221,8 +238,12 @@ class AscendFusedMoE(FusedMoE):
                     get_compressed_expert_map(self.expert_map))
         else:
             # init moe.
-            self.local_num_experts, self.expert_map = determine_expert_map(
-                self.ep_size, self.ep_rank, self.global_num_experts)
+            if vllm_version_is("0.11.0"):
+                self.local_num_experts, self.expert_map = determine_expert_map(
+                    self.ep_size, self.ep_rank, self.global_num_experts)
+            else:
+                self.local_num_experts, self.expert_map, _ = determine_expert_map(
+                    self.ep_size, self.ep_rank, self.global_num_experts)
             # dynamic eplb initializing with not expert_map_path
             if self.dynamic_eplb:
                 self.global_redundant_expert_num = ascend_config.init_redundancy_expert