CPU-Hybrid-MoE/DeepSeek-R1-0528-CPU-NUMA2-AMXINT4

Mirrored from https://modelscope.cn/models/ApproachingAI2024/DeepSeek-R1-0528-CPU-weight

For inference with sglang and kt-kernel: https://lmsys.org/blog/2025-10-22-KTransformers/

This version is packed specifically for NUMA tensor parallel = 2

当前模型精度为 experts AMXINT4