EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Drop 0.11.0 support (#4377)

Browse Source 
There is a lot hack code for v0.11.0, which makes the code hard to
upgrade to newer vLLM version. Since v0.11.0 will release soon. Let's
drop v0.11.0 support first. Then we'll upgrade to v0.11.2 soon.


- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-11-24 17:08:20 +08:00
committed by GitHub
parent 41ddb06554
commit a1f142b7ad
80 changed files with 467 additions and 1755 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
vllm_ascend/distributed/mooncake/mooncake_store.py
View File

@@ -6,18 +6,13 @@ from mooncake.store import ReplicateConfig # type: ignore
from vllm.config import ParallelConfig
from vllm.distributed.parallel_state import get_tensor_model_parallel_rank
from vllm.utils import logger
from vllm.utils.network_utils import get_ip
from vllm_ascend.distributed.mooncake.config_data import MooncakeEngineKey
from vllm_ascend.distributed.mooncake.transfer_engine import get_global_te
from vllm_ascend.utils import vllm_version_is
from .config_data import MooncakeStoreConfig
if vllm_version_is("0.11.0"):
from vllm.utils import get_ip
else:
from vllm.utils.network_utils import get_ip
METADATA_BYTES_LEN = 24
BASE_PORT = int(os.getenv("VLLM_BASE_PORT", "8790"))