注册并分享邀请链接,可获得视频播放与邀请奖励。

Tri Dao
@tri_dao
Asst. Prof @PrincetonCS, Chief Scientist @togethercompute. Machine learning & systems.
加入 May 2012
665 正在关注    45.4K 粉丝
SSMs had the nice asymptotics but kept missing out on the inference goodies Transformers get for free like spec decode and quantization. Turns out we were just not caching the right thing. Same IO-aware trick behind FlashAttention, Mamba scan, paged KV. A lot of the big wins weren’t new architectures, just people taking memory IO seriously.
显示更多
0
4
305
22
转发到社区