Kernels (CUDA / Triton / Pallas)

What a kernel is, CUDA vs Triton vs Pallas, and the FlashAttention idea: tiling and online softmax.

0 / 11 solved

Question Tags Difficulty Success

cudakernel-launch +2

Easy —

tritonkernels +3

Medium —

pallastpu-dma

Hard —

occupancyregisters +3

Hard —

flashattentionkernels +1

Hard —

kernel-fusiongpu-memory +1

Hard —

pallasblockspec

Hard —

flash-attentiongpu-kernels +1

Hard —

flashattentiononline-softmax

Insane —

flash-attentionhopper +2

Insane —

pallastpu +2

Insane —

11 of 11 questions here are still unsolved.