muhtasham (@muhtasham9) 's Twitter Profile
muhtasham

@muhtasham9

In my pre-training years

ID: 1234075207486312448

linkhttps://muhtasham.github.io/blog/ calendar_today01-03-2020 11:17:25

1,1K Tweet

1,1K Followers

1,1K Following

okaris (@okarisman) 's Twitter Profile Photo

i’ve consulted for ai infra companies and startups. i also built and launched my own ai apps using those infras. but they failed me. local tools were painful. hosted ones were worse. everything felt disconnected and fragile. so at the start of 2025 i began building my own thing.

Quentin Anthony (@quentinanthon15) 's Twitter Profile Photo

The very first task I usually give new pretraining people is to run a tiny transformer, profile it, and understand it deeply. I wrote up a small tutorial covering this exact workflow. I talk about how to measure GPU perf, how to estimate tensor core speedup, etc. Take a look: