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>

tests/ut/kv_connector/test_mooncake_connector.py

@@ -13,13 +13,7 @@ from unittest.mock import MagicMock, patch
 import msgspec
 import zmq
 from vllm.distributed.parallel_state import GroupCoordinator
-
-from vllm_ascend.utils import vllm_version_is
-
-if vllm_version_is("0.11.0"):
-    from vllm.utils import make_zmq_path
-else:
-    from vllm.utils.network_utils import make_zmq_path
+from vllm.utils.network_utils import make_zmq_path
 
 fake_engine = types.ModuleType("mooncake.engine")
 fake_engine.TransferEngine = MagicMock()  # type: ignore[attr-defined]

tests/ut/kv_connector/utils.py

@@ -10,6 +10,7 @@ import torch
 from vllm import SamplingParams
 from vllm.config import (CacheConfig, DeviceConfig, KVTransferConfig,
                          ModelConfig, SchedulerConfig, VllmConfig)
+from vllm.utils.hashing import sha256
 from vllm.v1.core.kv_cache_utils import (get_request_block_hasher,
                                          init_none_hash)
 from vllm.v1.core.sched.scheduler import Scheduler
@@ -19,13 +20,6 @@ from vllm.v1.outputs import ModelRunnerOutput
 from vllm.v1.request import Request
 from vllm.v1.structured_output import StructuredOutputManager
 
-from vllm_ascend.utils import vllm_version_is
-
-if vllm_version_is("0.11.0"):
-    from vllm.utils import sha256
-else:
-    from vllm.utils.hashing import sha256
-
 EOS_TOKEN_ID = 50256
 
 
@@ -111,21 +105,14 @@ def create_scheduler(
         ],
     )
     vllm_config.cache_config.num_gpu_blocks = num_blocks
-    if vllm_version_is("0.11.0"):
-        return Scheduler(
-            vllm_config=vllm_config,
-            kv_cache_config=kv_cache_config,
-            log_stats=True,
-            structured_output_manager=StructuredOutputManager(vllm_config),
-        )
-    else:
-        return Scheduler(
-            vllm_config=vllm_config,
-            kv_cache_config=kv_cache_config,
-            log_stats=True,
-            block_size=block_size,
-            structured_output_manager=StructuredOutputManager(vllm_config),
-        )
+
+    return Scheduler(
+        vllm_config=vllm_config,
+        kv_cache_config=kv_cache_config,
+        log_stats=True,
+        block_size=block_size,
+        structured_output_manager=StructuredOutputManager(vllm_config),
+    )
 
 
 _none_hash_initialized = False