flash-attention-rdna3

flash-attention-rdna3

chelokot

FlashAttention-2 Triton kernel for AMD RDNA3 (gfx1100 / Radeon RX 7900 XT/XTX/GRE): forward, backward, and split-K decode

2 Stars
1 Forks
0 Watchers
Python Language
mit License
50.1 SrcLog Score
Cost to Build
$7.6K
Market Value
$6.0K

Growth over time

2 data points  ·  2026-07-26 → 2026-08-09
Stars Forks Watchers
💬

How do you feel about this project?

Ask AI about flash-attention-rdna3

Question copied to clipboard

What is the chelokot/flash-attention-rdna3 GitHub project? Description: "FlashAttention-2 Triton kernel for AMD RDNA3 (gfx1100 / Radeon RX 7900 XT/XTX/GRE): forward, backward, and split-K decode". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone flash-attention-rdna3

Clone via HTTPS

git clone https://github.com/chelokot/flash-attention-rdna3.git

Clone via SSH

[email protected]:chelokot/flash-attention-rdna3.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the flash-attention-rdna3 issue tracker:

Open GitHub Issues