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

fix mooncake layerwise connector (#3849)

Browse Source 
### What this PR does / why we need it?
fix a typo in mooncake layerwise connector. There is only `requests`,
instead of `request` in `connector_metadata`. This pr fixes this typo

- vLLM version: v0.11.0rc3
- vLLM main:
83f478bb19

Signed-off-by: liziyu <liziyu16@huawei.com>
This commit is contained in:
liziyu
2025-10-29 23:10:51 +08:00
committed by GitHub
parent 5f176ca992
commit 07873d9396
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm_ascend/distributed/mooncake_layerwise_connector.py
View File

@@ -1151,7 +1151,8 @@ class MooncakeLayerwiseConnectorWorker:
connector_metadata: MooncakeLayerwiseConnectorMetadata, connector_metadata: MooncakeLayerwiseConnectorMetadata,
**kwargs) -> None: **kwargs) -> None:
"""MooncakeLayerwiseConnector does not save explicitly.""" """MooncakeLayerwiseConnector does not save explicitly."""
if self.kv_role == 'kv_producer' and connector_metadata.request.keys(): if self.kv_role == 'kv_producer' and connector_metadata.requests.keys(
):
if self.pd_head_ratio != 1: if self.pd_head_ratio != 1:
if self.current_layer != 0: if self.current_layer != 0:
self.completion_event.wait() self.completion_event.wait()