cs.DCNov 5, 2026

ZYFA: Speed and Accuracy of FP8 FlashAttention on AMD CDNA4

Authors: Quentin Anthony, Ganesh Bikshandi, Praneeth Medepalli, Stephen Ebert

Organizations: Zyphra San Francisco, CA

Abstract

Attention is a core building block of frontier models and often dominates compute-bound prefill at long context. FP8 matrix instructions offer twice the peak throughput of BF16, but they accelerate only matrix multiplication, and the softmax between the two matrix multiplications of attention runs on vector units that FP8 does not accelerate. On the AMD Instinct MI355X, the vendor's AITER kernels reach 39% of peak FP8 matrix throughput at 32K tokens, compared with 49% in BF16. Attention is also more numerically sensitive to quantization than feed-forward layers, and unlike NVIDIA's Hopper and Blackwell GPUs, the MI355X does not track the completion of matrix instructions in hardware, so overlapping the softmax with the matrix multiplications depends on instruction order. We present ZYFA, prefill kernels for the MI355X built on three techniques: (1) computing each FP8 probability directly from its score with a multiply-add and an integer conversion instead of an exponential; (2) a ping-pong schedule in which one group of threads computes its softmax while another executes its matrix multiplications; and (3) scaling each block of probabilities up by a power of two before rounding, and normalizing by the sum of the rounded probabilities. On attention inputs captured from three models and timed at sustained clock speeds, ZYFA achieves 1.16-1.76x the throughput of AITER. On the Gaussian inputs of kernel benchmarks at 32K tokens, it achieves 1.26-1.37x at head dimension 128 and 1.99x for DeepSeek-style multi-head latent attention. The sustained clock of the MI355X depends on operand values, so throughput on random inputs does not reliably predict throughput on real model activations. At head dimension 128, ZYFA's numerical error is within a few percent of that of Composable Kernel and Triton and 62-78% lower than that of AITER's. The source code is available at https://github.com/Zyphra/zyfa.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Nov 6, 2026

Fused-Softmax for efficient quantized attention

Low-precision matrix throughput on modern GPUs is growing far faster than vector-arithmetic throughput. Attention therefore cannot realize the available GEMM performance because softmax has become the pipeline bottleneck. We introduce Fused-Softmax Attention, a training-free algorithm that reformulates and approximates softmax to fold its dominant operations into the attention GEMMs, moving work from vector units to matrix cores. Implemented for the AMD CDNA 4 architecture, our MXFP8, MXFP6 and MXFP4 kernels reach approximately 3.0, 4.0 and 4.6 PFLOP/s on an AMD Instinct MI355X GPU, yielding speedups of 2.1×2.1\times, 2.8×2.8\times and 3.2×3.2\times over the BF16 attention. Importantly, the additional error introduced by Fused-Softmax remains below the error floor set by quantizing the GEMM operands. On Wan2.2-T2V-A14B, a hybrid MXFP6/4 schedule delivers up to 2.05×2.05\times end-to-end speedup while preserving the visual quality of the outputs. The kernels ship in AMD's open-source AITER library, and they powered AMD's MLPerf Inference v6.1 Wan2.2 submission, which ran 1.7×1.7\times faster than AMD's previous-round result on the same hardware. Our results show that redesigning softmax to utilize the matrix pipeline enables attention to capitalize on continued growth in low-precision matrix throughput.
Sep 3, 2026

Hardware-Aware FP4 FlashAttention-4

Blackwell's 4-bit floating-point (FP4) tensor cores do not automatically make attention faster because softmax conversion and on-chip dependencies dominate once its matrix products shrink. We address this with Direct-P for noncausal inference and a causal path that passes the forward quantization directly into backward. Direct-P maps scores directly to FP4 probabilities and reaches up to 2.13×\times the bfloat16 (BF16) forward throughput on an NVIDIA GB200. The causal path reconstructs probabilities from saved quantized queries and keys and uses 8-bit floating-point (FP8) gradient operands, accelerating a complete single-GPU 8-billion-parameter update by up to 1.14×\times. Matched distributed training retains FP8 probabilities and values; every tested MXFP4 probability/value training trajectory diverges.
Nov 2, 2026

FLAMIA: FLAsh MIcroscaling Attention for Fast and Causally Safe Training on Blackwell

Attention remains a substantial computational cost in Transformer training, particularly at long context lengths. NVIDIA Blackwell GPUs provide high-throughput low-precision matrix multiplication, but exploiting it in attention requires addressing quantization overhead, causal information leakage through shared scales, and numerical inconsistencies between the forward and backward passes. We present FLAMIA, a family of attention kernels for Blackwell with MXFP8 and mixed NVFP4/FP8 training paths. Our design combines token-block scaling that reuses quantized operands across matrix orientations, targeted safeguards against scale-induced leakage, and consistent forward and backward computations. Fused quantization and architecture-specific kernel optimizations reduce overhead, while document-local scaling and workload-aware scheduling support variable-length documents directly in packed layouts without repacking. Across various causal packed-document workloads, the MXFP8 path accelerates the combined forward and backward attention call, including quantization, by factors of 1.101.10--1.40×1.40\times on B200 and 1.061.06--1.42×1.42\times on B300 relative to the fastest evaluated baseline for each workload. We validate training stability and quality preservation on pretraining Llama-style models. These results show how jointly designing quantization, training numerics, and document scheduling translates low-bit hardware throughput into practical attention acceleration.