hustnn

Is there initial performance result for cpu reference?

> In general the performance number on CPU is not as good as GPU, for both latency and throughput. However we do find there are two value proposition for vLLM...

hi @zhouyuan @bigPYJ1151 , Thanks for your great work! Do you have plan to public some results on cpu inference with vllm?

> > hi @zhouyuan @bigPYJ1151 , Thanks for your great work! Do you have plan to public some results on cpu inference with vllm? > > Hi @hustnn, > >...

Yes there are type mismatch error here: pipelineOuter( inner => { case x => exporter.processMessage(s"Message received in ${actorName}") receive(x) exporter.processMessage(s"Message processed in ${actorName}") })

I forked this project and plan to maintain it. You can try it here: https://github.com/hustnn/akka-mon 2016-09-29 14:04 GMT+08:00 Nathan [email protected]: > +1 > > — > You are receiving this...

Do you mean the delta-based computation should be considered at the beginning (e.g., from the data source)? Can you illustrate more detail on this?

duplicated with https://github.com/ByConity/ByConity/issues/1059, the fix will be included in the new version. @frankye1982

Hi @ozcelgozde , we have solved this issue and will pick to byconity soon and we will notify you once its done.

> > Hi @ozcelgozde , we have solved this issue and will pick to byconity soon and we will notify you once its done. > > Hi @hustnn : which...