121
MultiPath Transfer Engine: Breaking GPU and Host-Memory Bandwidth Bottlenecks in LLM Services
arXiv:2512.16056v1 Announce Type: new
Abstract: The limited bandwidth of PCIe has emerged as the critical bottleneck for large language model (LLM) performance, such as prefix cache fetching and model switching. Although intra-server multipath data transfer between GPU and host memory is theoretically possible, heterogeneous protocols such as PCIe and NVLink currently limit the bandwidth between host memory and GPUs to that of a single PICe link. This limitation resuals in underutilized intra-server bandwidth. To address this issue, we propose Multipath Memory Access (MMA), a scheme that, to the best of our knowledge, is the first to enalbe efficient multipath data transfer between GPU and host memory. MMA supports seamless deployment via dynamic library injection, enabling LLM applications to benefit from MMA without requiring any code modification. In our testbed, MMA significantly improves the data transfer bandwidth between the GPU and memory, achieving a peak bandwidth of 245 GB/s-representing a 4.62x speedup compared to the natice single-path bandwidth. End-to-end evaluations demonstrate that MMA reduces the time-to-first-token (TTFT) for LLM serving by 1.14x to 2.38x and decreases model-switching latency in vLLM's sleep mode by 1.12x to 2.48x.
Abstract: The limited bandwidth of PCIe has emerged as the critical bottleneck for large language model (LLM) performance, such as prefix cache fetching and model switching. Although intra-server multipath data transfer between GPU and host memory is theoretically possible, heterogeneous protocols such as PCIe and NVLink currently limit the bandwidth between host memory and GPUs to that of a single PICe link. This limitation resuals in underutilized intra-server bandwidth. To address this issue, we propose Multipath Memory Access (MMA), a scheme that, to the best of our knowledge, is the first to enalbe efficient multipath data transfer between GPU and host memory. MMA supports seamless deployment via dynamic library injection, enabling LLM applications to benefit from MMA without requiring any code modification. In our testbed, MMA significantly improves the data transfer bandwidth between the GPU and memory, achieving a peak bandwidth of 245 GB/s-representing a 4.62x speedup compared to the natice single-path bandwidth. End-to-end evaluations demonstrate that MMA reduces the time-to-first-token (TTFT) for LLM serving by 1.14x to 2.38x and decreases model-switching latency in vLLM's sleep mode by 1.12x to 2.48x.
Anonymous
No comments yet.