Testing extreme NVME offload (4 x Gen5x4) for DeepSeek R1Because PCI-E 5x16 (~60GB/s) is close to dual channel DDR5 bandwidth, this is the cheapest method to run huge models. Code: <a href="https://github.com/BlinkDL/fast.c">https://github.com/BlinkDL/fast.c</a>