wangyuanxiong

Results 10 comments of wangyuanxiong

> > > [@HwwwwwwwH](https://github.com/HwwwwwwwH) Is there a doc for the OmniStreaming mode for VLLM? Also In omni mode, some instructions can be challenging to follow. (our training data includes only...

> > > > > [@HwwwwwwwH](https://github.com/HwwwwwwwH) Is there a doc for the OmniStreaming mode for VLLM? Also In omni mode, some instructions can be challenging to follow. (our training data...

> @AllenDou Thanks for your reply, can you tell me how to add support for http requests on your branch? Thank you, or can you add this function if it...

The test results were not as expected, and the input and output methods were very confusing.

Hi! During the process of building docker on the server, I found that these dependencies need to be installed. ---Original--- From: "Lyu ***@***.***> Date: Thu, Oct 10, 2024 19:22 PM...

> Hi, @wangyuanxiong-hub > > > Hi! During the process of building docker on the server, I found that these dependencies need to be installed. > > […](#) > >...

> > This is invoked by `outlines`. LMDeploy latest main branch has restrict its version "outlines

> > maybe this operator is not supported > > Oh..We use this training-op for more efficient calculation. We'll solve this issue in next month. Hi, I am also troubled...

> > > We have prepared a plan on 300I Duo, could you help us test it? @zer0py2c @wangyuanxiong-hub @qiling1345 > > > > > > You can try running...