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

[Feature] Support async scheduling + PP (#32359)

Browse Source 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Wentao Ye
2026-01-15 12:06:23 -05:00
committed by GitHub
parent 6218034dd7
commit b34474bf2c
5 changed files with 16 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/v1/core/utils.py
View File

@@ -9,6 +9,7 @@ from vllm.config import (
ECTransferConfig,
KVTransferConfig,
ModelConfig,
ParallelConfig,
SchedulerConfig,
SpeculativeConfig,
VllmConfig,
@@ -53,6 +54,7 @@ def create_scheduler(
num_speculative_tokens: int | None = None,
skip_tokenizer_init: bool = False,
async_scheduling: bool = False,
pipeline_parallel_size: int = 1,
use_ec_connector: bool = False,
ec_role: str | None = None,
) -> Scheduler | AsyncScheduler:
@@ -133,6 +135,7 @@ def create_scheduler(
scheduler_config=scheduler_config,
model_config=model_config,
cache_config=cache_config,
parallel_config=ParallelConfig(pipeline_parallel_size=pipeline_parallel_size),
kv_transfer_config=kv_transfer_config,
speculative_config=speculative_config,
ec_transfer_config=ec_transfer_config,