SlipStream: Enabling HBF for GPU Systems by Mitigating the Latency and SRAM Overheads

arXiv:2611.14776v1 Announce Type: new Abstract: Large language model (LLM) inference demands ever more memory capacity for larger models and batch sizes. High-Bandwidth Flash (HBF) replaces the DRAM dies of HBM with NAND flash and provides up to 16x the capacity at comparable read bandwidth. However, HBF can incur a read latency of nearly 20$\mu$s, 20x that of HBM, so on-demand HBF accesses slow inference by up to 12.8x. Conventional cache-line prefetchers require 20x more in-flight tracking state to cover this latency. Tensor-streaming designs, such as H3, follow virtual-address order as opposed to kernel-demand order, and therefore need hundreds of megabytes of buffering.