[1/N][Refactor] Refactor code to adapt with vllm main (#3612)

### What this PR does / why we need it? This is the step 1 of refactoring code to adapt with vllm main, and this pr aligned with 17c540a993 1. refactor deepseek to the latest code arch as of 17c540a993 2. bunches of fixes due to vllm changes - Fix `AscendScheduler` `__post_init__`, caused by https://github.com/vllm-project/vllm/pull/25075 - Fix `AscendScheduler` init got an unexpected arg `block_size`, caused by https://github.com/vllm-project/vllm/pull/26296 - Fix `KVCacheManager` `get_num_common_prefix_blocks` arg, caused by https://github.com/vllm-project/vllm/pull/23485 - Fix `MLAAttention` import,caused by https://github.com/vllm-project/vllm/pull/25103 - Fix `SharedFusedMoE` import, caused by https://github.com/vllm-project/vllm/pull/26145 - Fix `LazyLoader` improt, caused by https://github.com/vllm-project/vllm/pull/27022 - Fix `vllm.utils.swap_dict_values` improt, caused by https://github.com/vllm-project/vllm/pull/26990 - Fix `Backend` enum import, caused by https://github.com/vllm-project/vllm/pull/25893 - Fix `CompilationLevel` renaming to `CompilationMode` issue introduced by https://github.com/vllm-project/vllm/pull/26355 - Fix fused_moe ops, caused by https://github.com/vllm-project/vllm/pull/24097 - Fix bert model because of `inputs_embeds`, caused by https://github.com/vllm-project/vllm/pull/25922 - Fix MRope because of `get_input_positions_tensor` to `get_mrope_input_positions`, caused by https://github.com/vllm-project/vllm/pull/24172 - Fix `splitting_ops` changes introduced by https://github.com/vllm-project/vllm/pull/25845 - Fix multi-modality changes introduced by https://github.com/vllm-project/vllm/issues/16229 - Fix lora bias dropping issue introduced by https://github.com/vllm-project/vllm/pull/25807 - Fix structured ouput break introduced by https://github.com/vllm-project/vllm/issues/26737 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? CI passed with existing test. - vLLM version: v0.11.0rc3 - vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0 --------- Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: Icey <1790571317@qq.com> Co-authored-by: Icey <1790571317@qq.com>
2025-10-24 16:55:08 +08:00
parent ec9ec78b53
commit cea0755b07
47 changed files with 1189 additions and 493 deletions
--- a/vllm_ascend/core/recompute_scheduler.py
+++ b/vllm_ascend/core/recompute_scheduler.py
@@ -35,7 +35,7 @@ from vllm.distributed.kv_transfer.kv_connector.v1.base import \
    KVConnectorMetadata
 from vllm.distributed.kv_transfer.kv_connector.v1.metrics import \
    KVConnectorStats
-from vllm.logger import init_logger
+from vllm.logger import logger
 from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
 from vllm.v1.core.encoder_cache_manager import (EncoderCacheManager,
                                                compute_encoder_budget)
@@ -55,7 +55,7 @@ from vllm.v1.spec_decode.metrics import SpecDecodingStats
 from vllm.v1.structured_output import StructuredOutputManager
 from vllm.v1.utils import ConstantList

-logger = init_logger(__name__)
+from vllm_ascend.utils import vllm_version_is


 class RecomputeScheduler(SchedulerInterface):
@@ -67,6 +67,7 @@ class RecomputeScheduler(SchedulerInterface):
        vllm_config: VllmConfig,
        kv_cache_config: KVCacheConfig,
        structured_output_manager: StructuredOutputManager,
+        block_size: Optional[int] = None,
        mm_registry: MultiModalRegistry = MULTIMODAL_REGISTRY,
        include_finished_set: bool = False,
        log_stats: bool = False,
@@ -586,9 +587,14 @@ class RecomputeScheduler(SchedulerInterface):
            self.kv_cache_config.kv_cache_groups)
        if self.running:
            any_request = self.running[0]
-            num_common_prefix_blocks = (
-                self.kv_cache_manager.get_num_common_prefix_blocks(
-                    any_request, len(self.running)))
+            if vllm_version_is("0.11.0"):
+                num_common_prefix_blocks = (
+                    self.kv_cache_manager.get_num_common_prefix_blocks(
+                        any_request, len(self.running)))
+            else:
+                num_common_prefix_blocks = (
+                    self.kv_cache_manager.get_num_common_prefix_blocks(
+                        any_request.request_id))

        # Construct the scheduler output.
        new_reqs_data = [
--- a/vllm_ascend/core/schedule_config.py
+++ b/vllm_ascend/core/schedule_config.py
@@ -59,7 +59,7 @@ class AscendSchedulerConfig(SchedulerConfig):
                scheduler_config[k] = getattr(ascend_scheduler_config, k)
        return cls(**scheduler_config)

-    def __post_init__(self) -> None:
+    def __post_init__(self, *args) -> None:
        self.max_num_encoder_input_tokens = self.max_num_batched_tokens
        self.encoder_cache_size = self.max_num_batched_tokens
        self.chunked_prefill_enabled = self.enable_chunked_prefill
--- a/vllm_ascend/core/scheduler.py
+++ b/vllm_ascend/core/scheduler.py
@@ -16,7 +16,7 @@
 #
 import time
 from collections import deque
-from typing import Iterable, Union
+from typing import Iterable, Optional, Union

 from vllm.config import VllmConfig
 from vllm.distributed.kv_events import KVEventBatch
@@ -32,27 +32,19 @@ from vllm.v1.outputs import ModelRunnerOutput
 from vllm.v1.request import Request, RequestStatus
 from vllm.v1.structured_output import StructuredOutputManager

+from vllm_ascend.utils import vllm_version_is
+

 class AscendScheduler(Scheduler):
    """This Scheduler extends vllm's original v1 scheduler
    with prefill-first scheduling strategy."""

-    def __init__(
-        self,
-        vllm_config: VllmConfig,
-        kv_cache_config: KVCacheConfig,
-        structured_output_manager: StructuredOutputManager,
-        mm_registry: MultiModalRegistry = MULTIMODAL_REGISTRY,
-        include_finished_set: bool = False,
-        log_stats: bool = False,
-    ) -> None:
-        super().__init__(vllm_config, kv_cache_config,
-                         structured_output_manager, mm_registry,
-                         include_finished_set, log_stats)
+    def _initialize_common(self) -> None:
+        """Initialize common attributes shared across all versions."""
        self.scheduled_req_ids: set[str] = set()
        self.running: list[Request] = []
-
        self.finished_prefill_reqs: deque[Request] = deque()
+
        enable_pd_transfer = getattr(self.scheduler_config,
                                     'enable_pd_transfer', False)
        decode_max_num_seqs = getattr(self.scheduler_config,
@@ -61,6 +53,29 @@ class AscendScheduler(Scheduler):
        self.decode_max_num_running_reqs = max(self.max_num_running_reqs,
                                               decode_max_num_seqs)

+    def __init__(
+        self,
+        vllm_config: VllmConfig,
+        kv_cache_config: KVCacheConfig,
+        structured_output_manager: StructuredOutputManager,
+        block_size: Optional[int] = None,
+        mm_registry: MultiModalRegistry = MULTIMODAL_REGISTRY,
+        include_finished_set: bool = False,
+        log_stats: bool = False,
+    ) -> None:
+        # Call the parent class's __init__ method
+        if vllm_version_is("0.11.0"):
+            super().__init__(vllm_config, kv_cache_config,
+                             structured_output_manager, mm_registry,
+                             include_finished_set, log_stats)
+        else:
+            super().__init__(vllm_config, kv_cache_config,
+                             structured_output_manager, block_size,
+                             mm_registry, include_finished_set, log_stats)
+
+        # Initialize common attributes
+        self._initialize_common()
+
    def schedule(self) -> SchedulerOutput:
        if self.scheduler_config.chunked_prefill_enabled:
            return super().schedule()
@@ -440,9 +455,14 @@ class AscendScheduler(Scheduler):
            self.kv_cache_config.kv_cache_groups)
        if self.running:
            any_request = self.running[0]
-            num_common_prefix_blocks = (
-                self.kv_cache_manager.get_num_common_prefix_blocks(
-                    any_request, len(self.running)))
+            if vllm_version_is("0.11.0"):
+                num_common_prefix_blocks = (
+                    self.kv_cache_manager.get_num_common_prefix_blocks(
+                        any_request, len(self.running)))
+            else:
+                num_common_prefix_blocks = (
+                    self.kv_cache_manager.get_num_common_prefix_blocks(
+                        any_request.request_id))

        # Construct the scheduler output.
        new_reqs_data = [
--- a/vllm_ascend/core/scheduler_dynamic_batch.py
+++ b/vllm_ascend/core/scheduler_dynamic_batch.py
@@ -16,6 +16,7 @@
 #
 import os
 import time
+from typing import Optional

 import pandas as pd
 from vllm.config import VllmConfig
@@ -32,6 +33,8 @@ from vllm.v1.kv_cache_interface import KVCacheConfig
 from vllm.v1.request import Request, RequestStatus
 from vllm.v1.structured_output import StructuredOutputManager

+from vllm_ascend.utils import vllm_version_is
+

 class BudgetRefiner:
    """This budget refiner can make dynamic adjustment to the token budget 
@@ -122,13 +125,19 @@ class SchedulerDynamicBatch(Scheduler):
        vllm_config: VllmConfig,
        kv_cache_config: KVCacheConfig,
        structured_output_manager: StructuredOutputManager,
+        block_size: Optional[int] = None,
        mm_registry: MultiModalRegistry = MULTIMODAL_REGISTRY,
        include_finished_set: bool = False,
        log_stats: bool = False,
    ) -> None:
-        super().__init__(vllm_config, kv_cache_config,
-                         structured_output_manager, mm_registry,
-                         include_finished_set, log_stats)
+        if vllm_version_is("0.11.0"):
+            super().__init__(vllm_config, kv_cache_config,
+                             structured_output_manager, mm_registry,
+                             include_finished_set, log_stats)
+        else:
+            super().__init__(vllm_config, kv_cache_config,
+                             structured_output_manager, block_size,
+                             mm_registry, include_finished_set, log_stats)
        self.running: list[Request] = []
        self.budget_refiner = BudgetRefiner(
            default_budget=self.scheduler_config.max_num_batched_tokens,
@@ -531,10 +540,14 @@ class SchedulerDynamicBatch(Scheduler):
            self.kv_cache_config.kv_cache_groups)
        if self.running:
            any_request = self.running[0]
-            num_common_prefix_blocks = (
-                self.kv_cache_manager.get_num_common_prefix_blocks(
-                    any_request, len(self.running)))
-
+            if vllm_version_is("0.11.0"):
+                num_common_prefix_blocks = (
+                    self.kv_cache_manager.get_num_common_prefix_blocks(
+                        any_request, len(self.running)))
+            else:
+                num_common_prefix_blocks = (
+                    self.kv_cache_manager.get_num_common_prefix_blocks(
+                        any_request.request_id))
        # Construct the scheduler output.
        new_reqs_data = [
            NewRequestData.from_request(