HBF Is For AI Model Weights, HBM Is For KV Cache
… Related Story SK hynix, In Collaboration With SanDisk, Unveils The New High Bandwidth Flash HBF Standard, Helping To Resolve AI Inference Bottlenecks, Targeting Up To 3TB/s Bandwidth HBM and the memory wall issue An AI model with 100 billion parameters and operating at fp16 compute level - so 2 byt… …