gfx1030

Here is 1 public repository matching this topic...

2kiss / flash-attention-rdna2

Exact FlashAttention for AMD RDNA2 (gfx1030 / RX 6800 XT), written in HIP. Drop-in replacement for flash-attn: 19.8 TFLOP/s forward, decode at 99% of HBM bandwidth.

amd attention hip rocm llm-inference flash-attention rdna2 gfx1030

Updated Jul 20, 2026
HIP

Add this topic to your repo

To associate your repository with the gfx1030 topic, visit your repo's landing page and select "manage topics."

Learn more