An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU

• URL: http://arxiv.org/abs/2603.16428v1
• Date: Tue, 17 Mar 2026 12:05:17 GMT
• Title: An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU
• Abstract summary: Fine-tuning Large Language Models (LLMs) has become essential for domain adaptation, but its memory-intensive property exceeds the capabilities of most GPU.<n>We present SlideFormer, a novel system designed for single-GPU environments.<n>A lightweight asynchronous engine that treats the GPU as a sliding window and overlaps GPU with CPU updates and multi-tier I/O.
• Score: 10.811837575220814
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fine-tuning Large Language Models (LLMs) has become essential for domain adaptation, but its memory-intensive property exceeds the capabilities of most GPUs. To address this challenge and democratize LLM fine-tuning, we present SlideFormer, a novel system designed for single-GPU environments. Our innovations are: (1) A lightweight asynchronous engine that treats the GPU as a sliding window and overlaps GPU computation with CPU updates and multi-tier I/O. (2) A highly efficient heterogeneous memory management scheme significantly reduces peak memory usage. (3) Optimized Triton kernels to solve key bottlenecks and integrated advanced I/O. This collaborative design enables fine-tuning of the latest 123B+ models on a single RTX 4090, supporting up to 8x larger batch sizes and 6x larger models. In evaluations, SlideFormer achieves 1.40x to 6.27x higher throughput while roughly halving CPU/GPU memory usage compared to baselines, sustaining >95% peak performance on both NVIDIA and AMD GPUs.

Related papers

• Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models [67.17268530365189]
  This paper showcases a memory-efficient training stack for Mixture-of-Experts (MoE) models.<n>It combines and specializes various existing and novel parallelism techniques at different layers and stages of the MoE model training pipeline.
  arXiv  Detail & Related papers  (2026-07-02T08:06:57Z)
• GaDE -- GPU-acceleration of time-dependent Dirac Equation for exascale [0.0]
  GaDE is designed to simulate the electron dynamics in atoms induced by electromagnetic fields in the relativistic regime.<n>We evaluate GaDE on the pre-exascale supercomputer LUMI, powered by AMD MI250X GPUs and Hewlett-Packard's Slingshot interconnect.
  arXiv  Detail & Related papers  (2025-12-25T14:47:36Z)
• A Scalable Multi-GPU Framework for Encrypted Large-Model Inference [5.966282323502589]
  Encrypted AI using fully homomorphic encryption (FHE) provides strong privacy guarantees.<n>Recent works proposed ASICs to accelerate FHE, but require expensive advanced manufacturing processes that constrain their computation.<n>This paper presents Cerium, a multi- GPU framework for FHE inference on large models.
  arXiv  Detail & Related papers  (2025-12-12T04:15:38Z)
• Minute-Long Videos with Dual Parallelisms [57.22737565366549]
  Diffusion Transformer (DiT)-based video diffusion models generate high-quality videos at scale but incur prohibitive processing latency and memory costs for long videos.<n>We propose a novel distributed inference strategy, termed DualParal.<n>Instead of generating an entire video on a single GPU, we parallelize both temporal frames and model layers across GPUs.
  arXiv  Detail & Related papers  (2025-05-27T11:55:22Z)
• APOLLO: SGD-like Memory, AdamW-level Performance [61.53444035835778]
  Large language models (LLMs) are notoriously memory-intensive during training.<n>Various memory-efficient Scals have been proposed to reduce memory usage.<n>They face critical challenges: (i) costly SVD operations; (ii) significant performance trade-offs compared to AdamW; and (iii) still substantial memory overhead to maintain competitive performance.
  arXiv  Detail & Related papers  (2024-12-06T18:55:34Z)
• MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs [55.95879347182669]
  MoE architecture is renowned for its ability to increase model capacity without a proportional increase in inference cost. MoE-Lightning introduces a novel CPU-GPU-I/O pipelining schedule, CGOPipe, with paged weights to achieve high resource utilization. MoE-Lightning can achieve up to 10.3x higher throughput than state-of-the-art offloading-enabled LLM inference systems for Mixtral 8x7B on a single T4 GPU (16GB)
  arXiv  Detail & Related papers  (2024-11-18T01:06:12Z)
• Multi-GPU RI-HF Energies and Analytic Gradients $-$ Towards High Throughput Ab Initio Molecular Dynamics [0.0]
  This article presents an optimized algorithm and implementation for calculating resolution-of-the-identity Hartree-Fock energies and analytic gradients using multiple Graphics Processing Units (GPUs) The algorithm is especially designed for high throughput emphab initio molecular dynamics simulations of small and medium size molecules (10-100 atoms)
  arXiv  Detail & Related papers  (2024-07-29T00:14:10Z)
• EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction [67.11722682878722]
  This work presents EfficientViT, a new family of high-resolution vision models with novel multi-scale linear attention. Our multi-scale linear attention achieves the global receptive field and multi-scale learning. EfficientViT delivers remarkable performance gains over previous state-of-the-art models.
  arXiv  Detail & Related papers  (2022-05-29T20:07:23Z)
• Adaptive Elastic Training for Sparse Deep Learning on Heterogeneous Multi-GPU Servers [65.60007071024629]
  We show that Adaptive SGD outperforms four state-of-the-art solutions in time-to-accuracy. We show experimentally that Adaptive SGD outperforms four state-of-the-art solutions in time-to-accuracy.
  arXiv  Detail & Related papers  (2021-10-13T20:58:15Z)
• GPU Domain Specialization via Composable On-Package Architecture [0.8240720472180706]
  Composable On-PAckage GPU (COPAGPU) architecture to provide domain-specialized GPU products. We show how a COPA-GPU enables DL-specialized products by modular augmentation of the baseline GPU architecture with up to 4x higher off-die bandwidth, 32x larger on-package cache, 2.3x higher DRAM bandwidth and capacity, while conveniently supporting scaled-down HPC-oriented designs.
  arXiv  Detail & Related papers  (2021-04-05T23:06:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.