Industry
Mixture-of-Experts kernel engineering on Amazon SageMaker AI
AWS engineers share kernel optimizations for fused Mixture-of-Experts (MoE) models on Amazon SageMaker AI: Swap-AB for WGMMA utilization, Triton backend routing for FP8 quantization, and eliminating T
AWS engineers share kernel optimizations for fused Mixture-of-Experts (MoE) models on Amazon SageMaker AI: Swap-AB for WGMMA utilization, Triton backend routing for FP8 quantization, and eliminating Triton JIT recompilation. Together they deliver up to 10% higher throughput and up to 9% faster Time to First Token on H200 GPUs.
Related
- Deploying Kimi K3 on Amazon SageMaker HyperPod and Amazon EKS
- Manage Amazon SageMaker HyperPod Spaces directly from SageMaker Studio
- Right-size generative AI endpoints with concurrency sweeps on Amazon SageMaker AI
Source: AWS ML Blog | 2026-10-13