AI Reports · Amazon · 2026-10-13 · Blog / commentary
Mixture-of-Experts kernel engineering on Amazon SageMaker AI
AWS engineers describe kernel optimizations for fused Mixture-of-Experts models on Amazon SageMaker AI. These include Swap-AB for better WGMMA utilization, Triton backend routing for FP8 quantization, and removing Triton JIT recompilation. Together they deliver up to 10% higher throughput and up to 9% faster time to first token on H200 GPUs.