AI Daybook
AI Daybook
Today's issue
Open Source & Tools

Zyphra releases ZYFA, FP8 FlashAttention for AMD MI355X up to 1.76x faster

Original titleZyphra ZYFA: FP8 FlashAttention for AMD MI355X, Up to 1.76x Faster

Outlet
MarkTechPost
Published
Importance
3/5

Summary

Zyphra released ZYFA, open-source FP8 and BF16 prefill attention kernels for AMD Instinct MI355X. On real model activations, the FP8 kernels run 1.16–1.76x faster than AMD's AITER with 62–78% lower error at head dimension 128.

Original excerpt

Zyphra released ZYFA, open-source FP8 and BF16 prefill attention kernels for AMD Instinct MI355X. On real model activations, its FP8 kernels run 1.16-1.76x faster than AMD’s AITER, with 62-78% lower error at head dimension 128. The post Zyphra ZYFA: FP8 FlashAttention for AMD MI355X, Up to 1.76x Faster appeared first on MarkTechPost.

#optimization#gpu#amd#fp8
Read the original
See all →