가입 후 초대 링크를 공유하면 동영상 재생 및 초대 보상을 받을 수 있습니다.

Philip Kiely
@philipkiely
Author of Inference Engineering | Building @baseten | Not an LLM (yet)
가입 December 2018
988 팔로잉 중    16.6K 팬
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.
더 보기
0
41
2.1K
211
커뮤니티로 전달