Drop 0.11.0 support (#4377)

There is a lot hack code for v0.11.0, which makes the code hard to
upgrade to newer vLLM version. Since v0.11.0 will release soon. Let's
drop v0.11.0 support first. Then we'll upgrade to v0.11.2 soon.


- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

vllm_ascend/spec_decode/eagle_proposer.py

@@ -5,13 +5,15 @@ import numpy as np
 import torch
 import torch.nn as nn
 from vllm.attention.layer import Attention
-from vllm.config import CUDAGraphMode, VllmConfig, get_layers_from_vllm_config
+from vllm.config import (CompilationMode, 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
+from vllm.utils.platform_utils import is_pin_memory_available
 from vllm.v1.core.sched.output import SchedulerOutput
 from vllm.v1.sample.metadata import SamplingMetadata
 from vllm.v1.spec_decode.metadata import SpecDecodeMetadata
@@ -22,14 +24,6 @@ from vllm_ascend.attention.attention_v1 import (AscendAttentionState,
                                                 AscendMetadata)
 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
-    from vllm.utils import is_pin_memory_available
-else:
-    from vllm.config import CompilationMode
-    from vllm.utils.platform_utils import is_pin_memory_available
 
 PADDING_SLOT_ID = -1
 
@@ -52,16 +46,9 @@ class EagleProposer(Proposer):
         self.hidden_size = vllm_config.speculative_config.draft_model_config.get_hidden_size(
         )
 
-        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.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(