Robert Shaw
Robert Shaw
@pseudotensor Can you open a PR?
It would be good to have an open discussion about this feature as there is a real debate about what should be in or out of scope for vllm
@kerthcet looks like the docs build failed
This looks great. Can you just add a short example of `run_batch.py` in `/examples`
LGTM. Waiting for the CI to pass
Thanks for the good work here
@wuisawesome ping me on slack and ill merge it
@andy-neuma PTAL
> The PR looks good to me (I didn't review the kernel code in detail though). Do you know how much it adds to the binary size? We need to...
@alexm-nm can you review this?