{
  "id": 14232869,
  "title": "Mixture-of-Experts kernel engineering on Amazon SageMaker AI",
  "url": "https://urgent.news/2026/10/13/mixture-of-experts-kernel-engineering-on-amazon-sagemaker-ai",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-13T15:17:09.000Z",
  "source": {
    "name": "AWS Machine Learning",
    "slug": "aws-machine-learning",
    "url": "https://aws.amazon.com/blogs/machine-learning/mixture-of-experts-kernel-engineering-on-amazon-sagemaker-ai/"
  },
  "original_language": "en",
  "account": null,
  "summary": "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.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 2,
    "also_reported_by": [
      {
        "outlet": "AWS Machine Learning",
        "title": "Deploy decision models with llama.cpp on Amazon SageMaker AI",
        "url": "https://urgent.news/2026/10/12/deploy-decision-models-with-llama-cpp-on-amazon-sagemaker-ai",
        "published": "2026-10-12T15:51:46.000Z"
      }
    ]
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}