Writing Speed-of-Light Flash Attention for 5090 in CUDA C++ (gau-nernst.github.io) | HN Screenshots

YHacker Newsscreenshots

Screenshot of gau-nernst.github.io: Writing Speed-of-Light Flash Attention for 5090 in CUDA C++

First screen, captured 1 year ago.

Looks similar

Screenshot of iaroslavelistratov.github.io: B200 Attention Kernel from Scratch to Near-SOTA in 60 Diagrams

B200 Attention Kernel from Scratch to Near-SOTA in 60 Diagrams (iaroslavelistratov.github.io)

13 points by magoghm 1 month ago | 0 comments

Screenshot of aminediro.com: I rebuilt FlashAttention in Triton to understand the performance archaeology

I rebuilt FlashAttention in Triton to understand the performance archaeology (aminediro.com)

78 points by amindiro 10 months ago | 17 comments

Screenshot of winwang.blog: Faster sorting with SIMD CUDA intrinsics (2024)

Faster sorting with SIMD CUDA intrinsics (2024)(winwang.blog)

73 points by winwang 1 year ago | 9 comments

Screenshot of siboehm.com: How to optimize a CUDA matmul kernel for cuBLAS-like performance (2022)

How to optimize a CUDA matmul kernel for cuBLAS-like performance (2022)(siboehm.com)

86 points by mpweiher 2 years ago | 21 comments

Screenshot of elliotarledge.com: Batmobile: 10-20x Faster CUDA Kernels for Equivariant Graph Neural Networks

Batmobile: 10-20x Faster CUDA Kernels for Equivariant Graph Neural Networks (elliotarledge.com)

83 points by ipnon 9 months ago | 11 comments

Screenshot of vgel.me: Writing a C compiler in 500 lines of Python (2023)

Writing a C compiler in 500 lines of Python (2023)(vgel.me)

231 points by ofou 1 year ago | 74 comments