SangBin Cho

sorry it's been slipped! I will take a look at it by tmrw!

Thanks for the contribution! Should we next resume the paged attn PR?

you mean using that flag gives you the error?

it'd be also great to try the latest master to see if it fixes the issue (or after 0.4.3 is released) because https://github.com/vllm-project/vllm/pull/4557 could be the root cause if you...

Hi, I am waiting for this PR! Is this planning to be merged soon? Also, can I ask when it is planned to be released?

Btw, do we plan to merge this soon?

@skrider It looks like rebasing was pretty easy. would you mind if I just create a PR to your branch? (I just ran git merge main, and no conflict)

I think those are not working with long context multi lora. In order to get it working, I think other rotary embedding should also support multi scaling factors like we...

cc @mattip can you follow up and triage?

The core failure is fixed. Removing a release blocker. Seems like there's still discussion going on, so I will keep the issue open (@stephanie-wang let us know the priority of...