[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/spec_decode/eagle_proposer.py

@@ -5,10 +5,10 @@ import numpy as np
 import torch
 import torch.nn as nn
 from vllm.attention.layer import Attention
-from vllm.config import (CompilationLevel, CUDAGraphMode, VllmConfig,
-                         get_layers_from_vllm_config)
+from vllm.config import CUDAGraphMode, VllmConfig, get_layers_from_vllm_config
 from vllm.distributed.parallel_state import get_pp_group
 from vllm.logger import logger
+from vllm.model_executor.layers.attention_layer_base import AttentionLayerBase
 from vllm.model_executor.model_loader import get_model
 from vllm.model_executor.models import supports_multimodal
 from vllm.model_executor.models.llama_eagle3 import Eagle3LlamaForCausalLM
@@ -21,6 +21,12 @@ from vllm_ascend.attention.attention_mask import AttentionMaskBuilder
 from vllm_ascend.attention.attention_v1 import AscendAttentionState
 from vllm_ascend.attention.utils import AscendCommonAttentionMetadata
 from vllm_ascend.spec_decode.interface import Proposer, SpecDcodeType
+from vllm_ascend.utils import vllm_version_is
+
+if vllm_version_is("0.11.0"):
+    from vllm.config import CompilationLevel
+else:
+    from vllm.config import CompilationMode
 
 PADDING_SLOT_ID = -1
 
@@ -43,9 +49,17 @@ class EagleProposer(Proposer):
         self.hidden_size = vllm_config.speculative_config.draft_model_config.get_hidden_size(
         )
 
-        self.use_cuda_graph = (self.vllm_config.compilation_config.level
-                               == CompilationLevel.PIECEWISE and
-                               not self.vllm_config.model_config.enforce_eager)
+        if vllm_version_is("0.11.0"):
+            self.use_cuda_graph = (
+                self.vllm_config.compilation_config.level
+                == CompilationLevel.PIECEWISE
+                and not self.vllm_config.model_config.enforce_eager)
+        else:
+            self.use_cuda_graph = (
+                self.vllm_config.compilation_config.mode
+                == CompilationMode.VLLM_COMPILE
+                and not self.vllm_config.model_config.enforce_eager)
+
         self.cudagraph_batch_sizes = list(
             reversed(
                 self.vllm_config.compilation_config.cudagraph_capture_sizes))
@@ -80,9 +94,9 @@ class EagleProposer(Proposer):
         self.model = get_model(vllm_config=self.vllm_config,
                                model_config=self.vllm_config.
                                speculative_config.draft_model_config)
-        draft_attn_layer_names = (
-            get_layers_from_vllm_config(self.vllm_config, Attention).keys() -
-            target_attn_layer_names)
+        draft_attn_layer_names = (get_layers_from_vllm_config(
+            self.vllm_config, AttentionLayerBase).keys() -
+                                  target_attn_layer_names)
         self.attn_layer_name = next(iter(draft_attn_layer_names))
 
         # share embed_tokens with the target model if needed

vllm_ascend/spec_decode/mtp_proposer.py

@@ -4,10 +4,10 @@ import torch
 import torch.nn as nn
 import torchair
 from torchair import patch_for_hcom
-from vllm.attention.layer import Attention
 from vllm.config import (CUDAGraphMode, VllmConfig,
                          get_layers_from_vllm_config, set_current_vllm_config)
 from vllm.forward_context import BatchDescriptor, get_forward_context
+from vllm.model_executor.layers.attention_layer_base import AttentionLayerBase
 from vllm.model_executor.model_loader import get_model_loader
 from vllm.model_executor.model_loader.utils import (
     process_weights_after_loading, set_default_torch_dtype)
@@ -74,7 +74,8 @@ class MtpProposer(Proposer):
         loader = get_model_loader(self.vllm_config.load_config)
 
         target_attn_layer_names = set(
-            get_layers_from_vllm_config(self.vllm_config, Attention).keys())
+            get_layers_from_vllm_config(self.vllm_config,
+                                        AttentionLayerBase).keys())
         draft_model_config = \
             self.vllm_config.speculative_config.draft_model_config
         target_device = self.vllm_config.device_config.device
@@ -91,9 +92,9 @@ class MtpProposer(Proposer):
                 self.model = DeepSeekMTP(
                     vllm_config=self.vllm_config).to(target_device)
 
-        draft_attn_layer_names = (
-            get_layers_from_vllm_config(self.vllm_config, Attention).keys() -
-            target_attn_layer_names)
+        draft_attn_layer_names = (get_layers_from_vllm_config(
+            self.vllm_config, AttentionLayerBase).keys() -
+                                  target_attn_layer_names)
 
         assert len(draft_attn_layer_names) == 1
         self.attn_layer_name = list(draft_attn_layer_names)