20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[V1][Core] Remove unused speculative config from scheduler (#15818)

Browse Source 
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
This commit is contained in:
Mark McLoughlin 2025-03-31 20:15:21 +01:00 committed by GitHub
parent d4bfc23ef0
commit f98a4920f9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 1 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tests/v1/core/test_scheduler.py
View File

@ -71,7 +71,6 @@ def create_scheduler(
scheduler_config,
model_config,
cache_config,
speculative_config=None,
lora_config=None,
log_stats=True,
structured_output_manager=StructuredOutputManager(vllm_config),

5
vllm/v1/core/sched/scheduler.py
View File

@ -7,8 +7,7 @@ from collections import deque
from collections.abc import Iterable
from typing import Optional, Union
from vllm.config import (CacheConfig, LoRAConfig, ModelConfig, SchedulerConfig,
SpeculativeConfig)
from vllm.config import CacheConfig, LoRAConfig, ModelConfig, SchedulerConfig
from vllm.logger import init_logger
from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalRegistry
from vllm.v1.core.encoder_cache_manager import (EncoderCacheManager,
@ -36,7 +35,6 @@ class Scheduler(SchedulerInterface):
model_config: ModelConfig,
cache_config: CacheConfig,
lora_config: Optional[LoRAConfig],
speculative_config: Optional[SpeculativeConfig],
structured_output_manager: StructuredOutputManager,
mm_registry: MultiModalRegistry = MULTIMODAL_REGISTRY,
include_finished_set: bool = False,
@ -45,7 +43,6 @@ class Scheduler(SchedulerInterface):
self.scheduler_config = scheduler_config
self.cache_config = cache_config
self.lora_config = lora_config
self.speculative_config = speculative_config
self.log_stats = log_stats
self.structured_output_manager = structured_output_manager

1
vllm/v1/engine/core.py
View File

@ -95,7 +95,6 @@ class EngineCore:
model_config=vllm_config.model_config,
cache_config=vllm_config.cache_config,
lora_config=vllm_config.lora_config,
speculative_config=vllm_config.speculative_config,
include_finished_set=vllm_config.parallel_config.data_parallel_size
> 1,
log_stats=self.log_stats,