AI transport libraries move bytes efficiently, but they commonly assume that buffers are already correctly allocated, placed, shared, registered, and safe under completion and teardown pressure. This paper presents dmaplane, a Linux kernel module that makes this missing layer explicit as buffer orchestration. dmaplane exposes a stable kernel UAPI via /dev/dmaplane and composes ring-based command channels, DMA buffer lifecycle management, dma-buf export for cross-device sharing, a kernel-space RDMA engine, NUMA-aware allocation and verification, credit-based flow control, low-overhead observability, and GPU memory integration via PCIe BAR pinning. We evaluate orchestration sensitivity with measurements of NUMA cross-node penalties at DRAM scale, completion-safe flow control under sustained RDMA load, and GPU BAR mapping tiers versus cudaMemcpy. We also demonstrate end-to-end disaggregated inference by transferring KV-cache chunks between two machines using RDMA WRITE WITH IMMEDIATE and reconstructing tensor views on the receiver. RDMA measurements use Soft-RoCE; we distinguish measured results from provider-independent properties by construction.

翻译：AI传输库能够高效移动字节，但通常假设缓冲区已正确分配、放置、共享、注册，并在完成和拆卸压力下保持安全。本文提出dmaplane——一个将缺失层显式化为缓冲区编排的Linux内核模块。dmaplane通过/dev/dmaplane暴露稳定的内核UAPI，并组合了基于环的命令通道、DMA缓冲区生命周期管理、用于跨设备共享的dma-buf导出、内核空间RDMA引擎、NUMA感知分配与验证、基于信用的流控、低开销可观测性，以及通过PCIe BAR引脚固定的GPU内存集成。我们通过DRAM规模下NUMA跨节点惩罚的测量、持续RDMA负载下完成安全的流控，以及GPU BAR映射层级与cudaMemcpy的对比，评估了编排敏感性。我们还通过使用RDMA WRITE WITH IMMEDIATE在两台机器间传输KV-cache块，并在接收端重建张量视图，演示了端到端解耦推理。RDMA测量使用Soft-RoCE；我们通过构造区分测量结果与供应商无关属性。