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/models/qwen2_vl.py

@@ -38,13 +38,10 @@ from vllm.model_executor.models.qwen2_vl import (
     Qwen2VLForConditionalGeneration, Qwen2VLMultiModalProcessor,
     Qwen2VLProcessingInfo)
 from vllm.model_executor.models.utils import maybe_prefix
+from vllm.model_executor.models.vision import conv3d_to_linear_weight
 from vllm.multimodal import MULTIMODAL_REGISTRY
 
-from vllm_ascend.utils import (ACL_FORMAT_FRACTAL_ND, is_enable_nz,
-                               vllm_version_is)
-
-if not vllm_version_is("0.11.0"):
-    from vllm.model_executor.models.vision import conv3d_to_linear_weight
+from vllm_ascend.utils import ACL_FORMAT_FRACTAL_ND, is_enable_nz
 
 MIN_PAD_SIZE = 64  # min_size to pad weight
 MAX_PAD_SIZE = 128  # max_size to pad weight
@@ -308,9 +305,8 @@ class AscendQwen2VisionTransformer(Qwen2VisionTransformer):
         loaded_params: Set[str] = set()
 
         for name, loaded_weight in weights:
-            if not vllm_version_is("0.11.0"):
-                if name.endswith("patch_embed.proj.weight"):
-                    loaded_weight = conv3d_to_linear_weight(loaded_weight)
+            if name.endswith("patch_embed.proj.weight"):
+                loaded_weight = conv3d_to_linear_weight(loaded_weight)
 
             for (param_name, weight_name, shard_id) in stacked_params_mapping:
                 if weight_name not in name: