[Refactor] Import global var form vllm instead of overwirte it (#5469)

### What this PR does / why we need it?
Import global var form vllm instead of overwirte it, so that we could
use the correct global variant value

- vLLM version: v0.13.0
- vLLM main:
5326c89803
---------
Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2026-01-07 18:41:45 +08:00
committed by GitHub
parent 380f089fbf
commit 3f4f2b4ae6
10 changed files with 7 additions and 157 deletions

View File

@@ -32,6 +32,7 @@ from vllm.v1.core.sched.output import SchedulerOutput
from vllm.v1.kv_cache_interface import KVCacheConfig
from vllm_ascend.ascend_config import get_ascend_config
from vllm_ascend.distributed.mooncake_connector import GET_META_MSG
from vllm_ascend.distributed.mooncake_transfer_engine import global_te
from vllm_ascend.distributed.utils import (align_memory,
get_transfer_timeout_value,
@@ -44,7 +45,6 @@ if TYPE_CHECKING:
from vllm.v1.core.kv_cache_manager import KVCacheBlocks
from vllm.v1.request import Request
GET_META_MSG = b"get_meta_msg"
DONE_SENDING_MSG = b"done_sending_msg"