SemiAnalysis@SemiAnalysis_ · XAI 摘要
本周 InferenceX 团队讨论了将 DeepSeek V4 部署到 InferenceX 所需的工作、模型架构的变化、什么是 MegaKernel，以及在包括华为昇腾 NPU 在内的各种加速器上的初始性能。
This week the InferenceX team discusses what it took to get DeepSeek V4 on InferenceX， changes in the model architecture， what is a MegaKernel， and initial performance on various accelerators including Huawei Ascend NPUs.