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

[bugfix_v0.11.0]cancel tokenize for layerwise_proxy (#3913)

Browse Source 
### What this PR does / why we need it?
cancel tokenize for layerwise_proxy
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
by ci

Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
This commit is contained in:
wangxiaoteng888
2025-10-30 23:55:04 +08:00
committed by GitHub
parent af7a56550b
commit 38afd2c9cb
2 changed files with 1 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/distributed/mooncake_layerwise_connector.py
View File

@@ -656,7 +656,7 @@ class MooncakeLayerwiseConnectorWorker:
self.device_id = device_ids[self.tp_rank] # type: ignore
if vllm_config.kv_transfer_config.get_from_extra_config(
'use_ascend_direct', True):
'use_ascend_direct', False):
hostname = self.side_channel_host
else:
hostname = f"{self.side_channel_host}:0:npu_{self.device_id}"