---
format: "aidr-story-markdown/v1"
id: "012feed26f8d0194a0737d3d30cb80eaf6da708db5ddaa44727d77014ce6d71f"
canonical_url: "https://aidr.today/012feed2?lang=en"
title: "Zyphra ZYFA: FP8 FlashAttention for AMD MI355X, Up to 1.76x Faster"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-06T17:28:04.000Z"
category: "Open Source"
topics: ["inference","open-source"]
source_urls: ["https://www.marktechpost.com/2026/11/06/zyphra-zyfa-fp8-flashattention-amd-mi355x/"]
summary: "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."
---

# Zyphra ZYFA: FP8 FlashAttention for AMD MI355X, Up to 1\.76x Faster

> [Open the canonical story](<https://aidr.today/012feed2?lang=en>)

**Published:** 2026-11-06T17:28:04.000Z
**Category:** Open Source
**Topics:** inference, open\-source

## Summary

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\.

## Sources

- [Story source](<https://www.marktechpost.com/2026/11/06/zyphra-zyfa-fp8-flashattention-amd-mi355x/>)