[bugfix][refactor] fix recompute_scheduler break with vllm 0.12.0 & support async scheduling & refactor recompute_scheduler.py (#4895)

### What this PR does / why we need it?
Currently, the initialization and fundamental functions of
RecomputeScheduler are broken with `vLLM v0.12.0`. This PR fixes the
conflicts of `RecomputeScheduler` and refactor its implementations by
inheriting original `Scheduler` of vLLM. Meanwhile, this PR also
supports async cheduling with recompute scheduler by implementing
`AsyncRecomputeScheduler` which is simply inherited `AsncyScheduler` of
vLLM and `RecomputeScheduler` of vLLM-Ascend with python MRO.
### Does this PR introduce _any_ user-facing change?
No. The switch naming is the same as v0.11.0 :
`recompute_scheduler_enable`
### How was this patch tested?
E2E serving with 2P1D dsv3.1 passed. The performance was the same as
original vllm scheduler with `async_scheduling` and preempted requests
in D Nodes are successfully transfered to Proxy and further to P Node.
This significantly improves the performance and robustness of PD
disaggregation deployments.


- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: linfeng-yuan <1102311262@qq.com>

vllm_ascend/core/recompute_schedule_config.py

@@ -1,39 +0,0 @@
-#
-# Copyright (c) 2025 Huawei Technologies Co., Ltd. All Rights Reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-# This file is a part of the vllm-ascend project.
-#
-
-from dataclasses import dataclass, fields
-from typing import Type, Union
-
-from vllm.config import SchedulerConfig
-
-MAX_INT = 2147483647
-
-
-@dataclass
-class RecomputeSchedulerConfig(SchedulerConfig):
-    scheduler_cls: Union[str, Type[object]] = (
-        "vllm_ascend.core.recompute_scheduler.RecomputeScheduler")
-
-    @classmethod
-    def initialize_from_config(cls, vllm_scheduler_config: SchedulerConfig):
-        scheduler_config = {
-            field.name: getattr(vllm_scheduler_config, field.name)
-            for field in fields(vllm_scheduler_config) if field.init
-        }
-        scheduler_config["scheduler_cls"] = (
-            "vllm_ascend.core.recompute_scheduler.RecomputeScheduler")
-        return cls(**scheduler_config)

vllm_ascend/platform.py

@@ -298,10 +298,9 @@ class NPUPlatform(Platform):
             compilation_config.custom_ops = ["all"]
 
         if ascend_config.recompute_scheduler_enable:
-            from vllm_ascend.core.recompute_schedule_config import \
-                RecomputeSchedulerConfig
+            from vllm_ascend.core.recompute_scheduler import RecomputeSchedulerConfig
             recompute_scheduler_config = RecomputeSchedulerConfig.initialize_from_config(
-                vllm_config.scheduler_config)
+                vllm_config)
             vllm_config.scheduler_config = recompute_scheduler_config
 
         # Extend original scheduler_config to use SchedulerDynamicBatch.