Inferact
@inferact
Building the future of inference through @vllm_project
가입 December 2025
5 팔로잉 중 7K 팬
Thanks for the shoutout @SemiAnalysis_ ! Full breakdown linked here:
ALERT ALERT ALERT 🚨 🚨 🚨 VLLM MAINTAINERS HAVE JUST SHOWN THAT TPUv7 CAN GET 700 tok/s/user, 56% BETTER PERFORMANCE THAN NVIDIA GB200 NVL72 THROUGH MEGAKERNEL OPTIMIZATION ON KIMI K3.
As we said awhile ago, the TPU externalization of software is full steam ahead. This is ultra important to follow the progress of this.
더 보기
