simveit
simveit
@zhaochenyang20 can you please take a look at this.
> @simveit Hey simon. I made it rather concise. Could you use this version? Add keep contents like: > > Note: SGLang currently uses torch 2.5, so you need to...
@zhaochenyang20 i included your simpler way and it worked without the error i encountered before. only think i added was the transformers version we currently need.
> Hi, I'm not sure this is the right place to ask. I'm curious about the reasoning behind calculating the mean standard error. For measuring model consistency/uncertainty, the mean standard...
@shuaills @zhaochenyang20 I suggest to move docs like above from references to backend. Potential other candidate which I was not so sure about: * `supported_models.md` what do you think?
@zhaochenyang20 we definitely can. which ones are currently free from the points? described in other issue. than i can do the remaining ones here.
@zhaochenyang20 ohh i just see you did already the restructuring of docs :D
yes close this i create a clean branch than. i already talked to him.
Hello @tanzelin430 can you contact me in Slack channel or WeChat. I am Simon V on slack.
I opened [this issue](https://github.com/sgl-project/sglang/issues/3725) where I explain the experiment a little bit more detailed. @zhaochenyang20 I think we can close this issue in favor of the one i wrote. @tanzelin430...