註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Philip Kiely
@philipkiely
Author of Inference Engineering | Building @baseten | Not an LLM (yet)
加入 December 2018
988 正在關注    16.6K 粉絲
Scaling past a trillion parameters requires inference engineers to solve 3 issues: - Width: Routing between hundreds of sparse experts - Depth: Mixing global and local linear attention - Length: Processing 1M-token sequences I asked Ali and Bryce to draw it up. They delivered.
顯示更多
0
41
2.1K
211
轉發到社區