Lequn Chen
@abcdabcd987
Faster and cheaper LLM inference.
参加 January 2012
674 フォロー中 1.7K ファン
Faster than DeepEP for Decode on ConnectX-7. First viable kernel on EFA. SM-Free RDMA transfer. Support prefill. (Maybe portable to other hardware as well)
人気のあるユーザー
