EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Drop 0.11.0 support (#4377)

Browse Source 
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>
This commit is contained in:
wangxiyuan
2025-11-24 17:08:20 +08:00
committed by GitHub
parent 41ddb06554
commit a1f142b7ad
80 changed files with 467 additions and 1755 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
vllm_ascend/core/recompute_scheduler.py
View File

@@ -55,8 +55,6 @@ from vllm.v1.spec_decode.metrics import SpecDecodingStats
from vllm.v1.structured_output import StructuredOutputManager
from vllm.v1.utils import ConstantList
from vllm_ascend.utils import vllm_version_is
class RecomputeScheduler(SchedulerInterface):
"""This Scheduler extends vllm's original v1 scheduler of version 0.11
@@ -587,14 +585,9 @@ class RecomputeScheduler(SchedulerInterface):
self.kv_cache_config.kv_cache_groups)
if self.running:
any_request = self.running[0]
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))
num_common_prefix_blocks = (
self.kv_cache_manager.get_num_common_prefix_blocks(
any_request.request_id))
# Construct the scheduler output.
new_reqs_data = [

33
vllm_ascend/core/scheduler.py
View File

@@ -22,14 +22,7 @@ from vllm.config import VllmConfig
from vllm.distributed.kv_events import KVEventBatch
from vllm.logger import logger
from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
from vllm_ascend.utils import vllm_version_is
if vllm_version_is("0.11.0"):
from vllm.utils import cdiv
else:
from vllm.utils.math_utils import cdiv
from vllm.utils.math_utils import cdiv
from vllm.v1.core.kv_cache_manager import KVCacheBlocks
from vllm.v1.core.sched.output import NewRequestData, SchedulerOutput
from vllm.v1.core.sched.scheduler import Scheduler
@@ -39,8 +32,6 @@ 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
@@ -71,14 +62,9 @@ class AscendScheduler(Scheduler):
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)
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()
@@ -462,14 +448,9 @@ class AscendScheduler(Scheduler):
self.kv_cache_config.kv_cache_groups)
if self.running:
any_request = self.running[0]
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))
num_common_prefix_blocks = (
self.kv_cache_manager.get_num_common_prefix_blocks(
any_request.request_id))
# Construct the scheduler output.
new_reqs_data = [

24
vllm_ascend/core/scheduler_dynamic_batch.py
View File

@@ -33,8 +33,6 @@ 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
@@ -130,14 +128,9 @@ class SchedulerDynamicBatch(Scheduler):
include_finished_set: bool = False,
log_stats: bool = False,
) -> None:
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)
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,
@@ -540,14 +533,9 @@ class SchedulerDynamicBatch(Scheduler):
self.kv_cache_config.kv_cache_groups)
if self.running:
any_request = self.running[0]
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))
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(