{"id":"caa121d3-5879-4e81-902d-ea3bb5911307","url":"https://api.tumn.com/news/caa121d3-5879-4e81-902d-ea3bb5911307","title":"Mixture-of-Experts kernel engineering on Amazon SageMaker AI","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 u","sections":[],"faq":[],"sources":[{"url":"https://aws.amazon.com/blogs/machine-learning/mixture-of-experts-kernel-engineering-on-amazon-sagemaker-ai/","title":"AWS Machine Learning Blog","publishedAt":"2026-10-13T15:17:09.000Z"}],"author":"TUMN 큐레이션","aiAssisted":false,"reviewStatus":"automated","reviewNote":"원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.","publishedAt":"2026-10-13T15:17:09.000Z","modifiedAt":"2026-10-13T22:24:54.000Z","checkedAt":"2026-10-13T22:24:54.942Z","language":"ko","kind":"link","sourceLabel":"AI 공식","profile":null,"via":null,"formats":{"json":"https://api.tumn.com/news/caa121d3-5879-4e81-902d-ea3bb5911307.json","markdown":"https://api.tumn.com/news/caa121d3-5879-4e81-902d-ea3bb5911307.md"}}