N
Hacker Next
new
past
show
ask
show
jobs
submit
login
▲
B200 Attention Kernel from Scratch to Near-SOTA in 60 Diagrams
(
iaroslavelistratov.github.io
)
23 points by
magoghm
1 days ago
|
3 comments
add comment
Rendered at 14:08:59 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
xiphias2 20 hours ago
[-]
Pretty cool, it's missing how these concepts map to ThunderKittens code (my favorite CUDA toolkit)
peter_d_sherman 15 hours ago
[-]
One of the best AI GPU Attention Kernel how-to-implement articles I've read in a long time!
Tremendous work, tremendous effort was placed into writing this article -- and it shows!
Well done!
erichocean 19 hours ago
[-]
Really interesting project, appreciated.
Tremendous work, tremendous effort was placed into writing this article -- and it shows!
Well done!