
Philip Kiely
@philipkiely • 16,437 subscribers
Author of Inference Engineering | Building @baseten | Not an LLM (yet)
Shorts
Videos

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.
Philip Kiely158,771 次观看 • 13 天前
没有更多内容可加载

