註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Sonnet Xu
@sonnet_xu
cs @ stanford || reliability + benchmarking, compute + llms
加入 January 2025
89 正在關注    1.3K 粉絲
inference is becoming a market-making business upstream, GPU capacity is bought in chunks: financed, contracted, take-or-pay, multi-year downstream, tokens are bought on demand warehousing the mismatch between the two means forecasting demand, absorbing idle capacity, and repricing compute into tokens neoclouds are moving down into inference and inference providers are moving up into GPUs whoever can make a market between fixed capacity and variable demand takes the spread
顯示更多
0
18
303
19
轉發到社區