在 NVIDIA DGX Spark 上提升 MoE 推理性能的 3 种方法
3 Ways to Boost MoE Inference on NVIDIA DGX Spark
NVIDIA 给出在 DGX Spark 上提升 MoE 推理性能的三种方法。对 Inclusion AI 的 Ling-3.0-flash 做 batch-size-1 评测时，性能分析显示解码受内存限制，读取模型权重是主要耗时来源，MoE 计算与输出层投影这两个操作尤为突出。
Generating tokens faster starts with identifying what limits inference performance. In the batch-size-1 evaluation of Ling-3.0-flash from Inclusion AI on NVIDIA...
Generating tokens faster starts with identifying what limits inference performance. In the batch-size-1 evaluation of Ling-3.0-flash from Inclusion AI on NVIDIA DGX Spark, profiling showed that decoding was memory-bound: reading model weights drove execution time. Two operations stood out—the mixture-of-experts (MoE) computation and the output-layer projection that produces scores across the model’…
来源：NVIDIA Developer Blog · developer.nvidia.com