Zyphra ships ZYFA: FP8 attention on AMD MI355X at 1.16-1.76x AITER throughput
bclavie · x · 2026-11-06
Zyphra introduced Zyphra FlashAttention (ZYFA), delivering faster and more accurate FP8 attention on AMD MI355X. Its prefill kernels achieve 1.16–1.76x the throughput of AMD's inference kernel library AITER on real model inputs at 16K tokens under sustained load.
More from Infra
- Is AMD 7900 XT/XTX viable for video generation in late 2026? — Beneficial_Fish_7509 · 2026-11-06
- Blue Origin unveils Northstar engine: 715,000 lbf thrust, 30% lighter than BE-4 — beffjezos · 2026-11-06
- DFlash drafts whole token blocks in parallel to fix speculative decoding bottleneck — Lianhuiq · 2026-11-06
- A single desktop B70 runs an entire AI livestream radio, generating music in real time — prince_pringle · 2026-11-06
- Inferact, founded by vLLM creators, now serves 7 trillion tokens a day — Xianbao_QIAN · 2026-11-06
- Q-CTRL launches Dynamics Simulator Qiskit Function on IBM Quantum — MJBiercuk · 2026-11-06