sunmac
Results
3
comments of
sunmac
k8s级别的调度，无法对节点的gpu显存进行限制的。
> ### Motivation > 我希望在海光的DCU上能拉起服务 > > ```shell > lmdeploy serve api_server /data/models/qwen/Qwen2-7B-Instruct \ > > --model-name Qwen2-7B-Instruct \ > > --server-port 8000 \ > > --tp 2 > 2024-08-27...
We encountered the same issue, but in the opposite direction: the dispatch bandwidth on the master node is low, while the combine bandwidth is high. The problem persists even after...