throwa356262 38 minutes ago

Better performance than TQ and better quality than FP16?

Am I reading this right??

v3ss0n 39 minutes ago

Why this is not a PR for vLLM ?

  • esafak 32 minutes ago

    It's the output of a research paper; the authors are not trying to build up vLLM, and they probably have no incentive to do so. You can submit a PR, though! It's easier now while the divergence is low, so don't wait. Since there are six authors, I bet you could get help with the inevitable review chores if you just take the step of creating the PR.

    edit: It might not be clear that it is based on vLLM 0.22, which is the current version: https://github.com/huawei-csl/KVarN/commit/d6290e99098d7426d...; all you have to do is create a diff off it. It's fairly straightforward.

    • jmalicki 18 minutes ago

      And with the help of AI, pointing at AI at this paper and saying "making a vLLM PR from this paper" tends to work surprisingly well, even if you need to nudge it a little bit along the way.