shangmingc

> @ShangmingCai Thanks for your reply, after go through #14824? It seems have no related to `Mooncakestore` since mooncake store use mooncake store connector AFAIK. Yes. However, some changes need...

> @ShangmingCai > > Is this change going into vLLM v0 or v1? > This is for v0. For v1, the design of disaggregated framework will changes, we will make...

> Nice work. But we have the following problems with reproducing. Can anyone give some advice? > @Second222None Please raise a new issue in the Mooncake repo, we will find...

@DarkLight1337 Any idea why v1-test keep failing?

@LiuXiaoxuanPKU Hello, I saw the RFC you wrote, so I took some time to implement this PR. According to the conversion script, we have to transform config.json to wrap it...

BTW, this PR is compatible with the old method with the conversion script. The converted config.json and weight binary can still be loaded successfully. After testing, the Draft acceptance rate...

> (1) Yeah, could you add simple tests here? A simplest test is just to test the weights of the proposer model's lm_head is the same as the weights of...

Sorry for triggering DCO misbehavior while trying to rebase the code to address an unknown doc build failure. It was a mistake. My bad.

> I'm trying this PR, but it seems there are some minor errors: @LiuXiaoxuanPKU Hello, thanks for the feedback, but I couldn't reproduce this `embed_tokens` error in my local environment....

> > I'm trying this PR, but it seems there are some minor errors: > > @LiuXiaoxuanPKU Hello, thanks for the feedback, but I couldn't reproduce this `embed_tokens` error in...