AWS Machine Learning Blog· Mona Mona·· 3 d ago
Mixture-of-Experts kernel engineering on Amazon SageMaker AI
Mixture-of-Experts kernel engineering on Amazon SageMaker AI
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 up to 9% faster Time to First Token on H200 GPUs.
Selection record
Threshold 60Official, first-handFirst 34Second 34
Not admittedSum of both 68 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：MoE内核工程与LLM推理优化
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: AWS Machine Learning Blog · aws.amazon.com