Swap-AB kernel and Triton backend speed up MoE inference on Hopper GPUs

AWS Machine Learning Blog describes a Swap-AB kernel change that flips the MoE matrix multiplication to match Hopper WGMMA layouts.

The change improves end-to-end output throughput by 2–4 percent across large MoE models on H200 and is available in vLLM 0.24.0 or later.

For FP8 tensor-quantized models on Hopper, the post says the Triton backend consistently outperforms the default FLASHINFER_CUTLASS path.