Show HN derives a FlashAttention kernel from about 25 lines of SQL
The Hacker News feed only shows the title, 20 points, and one comment.
4 stories, newest first · one card per story
The Hacker News feed only shows the title, 20 points, and one comment.
Neural tanh PDE solvers can miss finite limits as parameters diverge; kernel derivatives restore attainable approximations.
Researchers derive functional-gradient rules for retrieval-centric layers that grow by storing key-value pairs for every training point.
Hugging Face released @huggingface/kernels, a library offering 200+ WebGPU compute kernels to accelerate AI inference locally in browsers.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views