maharshi(@maharshii):i'll let you in on something: inference optimization has moved up the abstraction ladder. it's not about handwriting the fastest kernels anymore. it's about how well you can define your optimization context, I/O, constraints, and testing environment for your AI agents.

maharshi

@maharshii

learning deeply about life one gradient step at a time - ml perf optimizer @ fal

加入 May 2020

1.2K 正在關注 43.1K 粉絲

maharshi@maharshii

2026.10.05 15:34

i'll let you in on something: inference optimization has moved up the abstraction ladder. it's not about handwriting the fastest kernels anymore. it's about how well you can define your optimization context, I/O, constraints, and testing environment for your AI agents.

644

轉發到社區

熱門用戶