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

[V1] Scheduler Refactoring [1/N] - Add Scheduler Interface (#15250)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Cody Yu <hao.yu.cody@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
This commit is contained in:
Woosuk Kwon
2025-03-20 17:50:43 -07:00
committed by GitHub
parent 06dd08256f
commit 0c6f5023c3
17 changed files with 182 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/v1/attention/backends/flash_attn.py
View File

@@ -17,7 +17,7 @@ from vllm.platforms import current_platform
from vllm.utils import cdiv
if TYPE_CHECKING:
from vllm.v1.core.scheduler_output import SchedulerOutput
from vllm.v1.core.sched.output import SchedulerOutput
from vllm.v1.worker.gpu_input_batch import InputBatch
from vllm.v1.worker.gpu_model_runner import GPUModelRunner

2
vllm/v1/attention/backends/mla/common.py
View File

@@ -212,7 +212,7 @@ except ImportError:
from flash_attn import flash_attn_varlen_func
if TYPE_CHECKING:
from vllm.v1.core.scheduler_output import SchedulerOutput
from vllm.v1.core.sched.output import SchedulerOutput
from vllm.v1.worker.gpu_input_batch import InputBatch
from vllm.v1.worker.gpu_model_runner import GPUModelRunner