biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V1][Minor] Move scheduler outputs to a separate file (#13062)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-02-10 18:10:06 -08:00
committed by GitHub
parent 91e876750e
commit 2ff4857678
4 changed files with 113 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/worker/gpu_model_runner.py
View File

@@ -36,7 +36,7 @@ from vllm.v1.worker.gpu_input_batch import CachedRequestState, InputBatch
from vllm.v1.worker.lora_model_runner_mixin import LoRAModelRunnerMixin
if TYPE_CHECKING:
from vllm.v1.core.scheduler import SchedulerOutput
from vllm.v1.core.scheduler_output import SchedulerOutput
logger = init_logger(__name__)

3
vllm/v1/worker/gpu_worker.py
View File

@@ -18,7 +18,6 @@ from vllm.logger import init_logger
from vllm.model_executor import set_random_seed
from vllm.platforms import current_platform
from vllm.utils import GiB_bytes
from vllm.v1.core.scheduler import SchedulerOutput
from vllm.v1.kv_cache_interface import KVCacheConfig, KVCacheSpec
from vllm.v1.outputs import ModelRunnerOutput
from vllm.v1.worker.gpu_model_runner import GPUModelRunner
@@ -26,7 +25,7 @@ from vllm.v1.worker.gpu_model_runner import GPUModelRunner
logger = init_logger(__name__)
if TYPE_CHECKING:
from vllm.v1.core.scheduler import SchedulerOutput
from vllm.v1.core.scheduler_output import SchedulerOutput
class Worker: