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_connector.py
View File

@@ -37,7 +37,7 @@ import vllm_ascend.envs as envs_ascend
from vllm_ascend.ascend_config import get_ascend_config, init_ascend_config
from vllm_ascend.distributed.mooncake.transfer_engine import get_global_te
from vllm_ascend.distributed.utils import get_transfer_timeout_value
from vllm_ascend.utils import prefill_context_parallel_enable, vllm_version_is
from vllm_ascend.utils import prefill_context_parallel_enable
# isort: off
if prefill_context_parallel_enable():
@@ -46,10 +46,7 @@ if prefill_context_parallel_enable():
)
# isort: on
if vllm_version_is("0.11.0"):
from vllm.utils import get_ip, make_zmq_path, make_zmq_socket
else:
from vllm.utils.network_utils import get_ip, make_zmq_path, make_zmq_socket
from vllm.utils.network_utils import get_ip, make_zmq_path, make_zmq_socket
if TYPE_CHECKING:
from vllm.attention.backends.abstract import AttentionMetadata