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

[bugfix]cancel tokenize for layerwise_proxy (#3914)

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

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
This commit is contained in:
wangxiaoteng888
2025-10-30 23:54:46 +08:00
committed by GitHub
parent eb0a2ee2d0
commit a2b325ee00
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

@@ -662,7 +662,7 @@ 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}"