| ▲ | B200 Attention Kernel from Scratch to Near-SOTA in 60 Diagrams(iaroslavelistratov.github.io) | |
| 24 points by magoghm 2 days ago | 3 comments | ||
| ▲ | xiphias2 2 days ago | parent | next [-] | |
Pretty cool, it's missing how these concepts map to ThunderKittens code (my favorite CUDA toolkit) | ||
| ▲ | peter_d_sherman a day ago | parent | prev | next [-] | |
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 2 days ago | parent | prev [-] | |
Really interesting project, appreciated. | ||