Online Softmax Tiling FlashAttention kernel executing bounded SRAM query/key/value block updates with running max and sum rescaling for O(1) memory footprint.
-
Updated
Sep 9, 2026 - Python
#
transformer-kernel
Here are 2 public repositories matching this topic...
Online Softmax Tiling FlashAttention kernel executing bounded SRAM query/key/value block updates with running max and sum rescaling for O(1) memory footprint.
-
Updated
Sep 9, 2026 - Python
Add this topic to your repo
To associate your repository with the transformer-kernel topic, visit your repo's landing page and select "manage topics."