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/worker/worker_v1.py

@@ -35,6 +35,8 @@ from vllm.logger import logger
 from vllm.lora.request import LoRARequest
 from vllm.sequence import IntermediateTensors
 from vllm.tasks import SupportedTask
+from vllm.utils.mem_constants import GiB_bytes
+from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
 from vllm.v1.core.sched.output import SchedulerOutput
 from vllm.v1.kv_cache_interface import KVCacheConfig, KVCacheSpec
 from vllm.v1.outputs import (EMPTY_MODEL_RUNNER_OUTPUT, AsyncModelRunnerOutput,
@@ -50,7 +52,7 @@ from vllm_ascend.platform import NPUPlatform
 from vllm_ascend.utils import (init_ascend_soc_version, is_enable_nz,
                                prefill_context_parallel_enable,
                                register_ascend_customop, sleep_mode_enabled,
-                               try_register_lib, vllm_version_is)
+                               try_register_lib)
 from vllm_ascend.worker.model_runner_v1 import NPUModelRunner
 
 torch._dynamo.trace_rules.clear_lru_cache()  # noqa: E402
@@ -65,12 +67,6 @@ torch_non_c_binding_in_graph_functions_npu[
 torch._dynamo.trace_rules.torch_name_rule_map.append(
     torch_non_c_binding_in_graph_functions_npu)  # noqa: E402
 
-if vllm_version_is("0.11.0"):
-    from vllm.utils import STR_DTYPE_TO_TORCH_DTYPE, GiB_bytes
-else:
-    from vllm.utils.mem_constants import GiB_bytes
-    from vllm.utils.torch_utils import STR_DTYPE_TO_TORCH_DTYPE
-
 
 class NPUWorker(WorkerBase):
 
@@ -141,10 +137,7 @@ class NPUWorker(WorkerBase):
 
         if self.model_config.trust_remote_code:
             # note: lazy import to avoid importing torch before initializing
-            if vllm_version_is("0.11.0"):
-                from vllm.utils import init_cached_hf_modules
-            else:
-                from vllm.utils.import_utils import init_cached_hf_modules
+            from vllm.utils.import_utils import init_cached_hf_modules
 
             init_cached_hf_modules()