‹ BackHN Continuity

Thread

How GLM built its own inference infrastructure

411 points · 285 comments · whiteros_e

  1. 9cb14c1ec0 · · focus · HN ↗
    Given the huge amount of money being spent on AI chips in the US, what prevents US AI labs from doing the same level of software optimization? It could be a solve for some of the capacity constraints.
    1. a012 · · focus · HN ↗
      > what prevents US AI labs from doing the same level of software optimization?

      Because they don’t have to. Most of the time money would buy you newest and/or more hardwares so there’s low/minimal interest to optimize the code or approach.

      1. Art9681 · · focus · HN ↗
        They are making these optimizations. They publish these reports too if you care to look.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.