Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Andrej Karpathy on Tensor Cores and TF32 precision

112,983 Aufrufe • vor 1 Jahr •via X (Twitter)

9 Kommentare

Profilbild von Tommy Falkowski
Tommy Falkowskivor 1 Jahr

He's an awesome teacher! I just love his clean style of explaining things!

Profilbild von ℏεsam
ℏεsamvor 1 Jahr

he really has it in him

Profilbild von Konstantin
Konstantinvor 1 Jahr

Can you share a full source please?

Profilbild von rogue node
rogue nodevor 1 Jahr

So basically TF32 is a lie.

Profilbild von Jacob Posel
Jacob Poselvor 1 Jahr

Where does he post this?

Profilbild von john
johnvor 1 Jahr

Lmao what are the odds that the moment I get to this part of the video on my first time watch, i see this on twitter right after

Profilbild von ℏεsam
ℏεsamvor 1 Jahr

i'm watching you :)

Profilbild von Felix Chin MD
Felix Chin MDvor 1 Jahr

TF32 just means ur neural net’s matmuls are running on 18-bit numerics (FP 18 precision) apple (mlx) easily lets u control this (by setting intermediate weights and values to FP 16) don’t see how TF32 is anything special. seems like a marketing gimmick

Profilbild von MarcoDagna e/acc 🇪🇸 ⌛️🌍
MarcoDagna e/acc 🇪🇸 ⌛️🌍vor 1 Jahr

@HeyGenLabs english spanish

Ähnliche Videos