FloE: On-the-Fly MoE Inference on Memory-constrained GPU

• URL: http://arxiv.org/abs/2505.05950v2
• Date: Mon, 12 May 2025 03:29:12 GMT
• Title: FloE: On-the-Fly MoE Inference on Memory-constrained GPU
• Authors: Yuxin Zhou, Zheng Li, Jun Zhang, Jue Wang, Yiping Wang, Zhongle Xie, Ke Chen, Lidan Shou,
• Abstract summary: FloE is built on the insight that there exists substantial untapped redundancy within sparsely activated experts.<n>FloE achieves a 9.3x compression of parameters per expert in Mixtral-8x7B.<n>It enables deployment on a GPU with only 11GB VRAM, reducing the memory footprint by up to 8.5x.
• Score: 22.2581000412208
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices. While offloading expert parameters to CPU memory and loading activated experts on demand has emerged as a potential solution, the large size of activated experts overburdens the limited PCIe bandwidth, hindering the effectiveness in latency-sensitive scenarios. To mitigate this, we propose FloE, an on-the-fly MoE inference system on memory-constrained GPUs. FloE is built on the insight that there exists substantial untapped redundancy within sparsely activated experts. It employs various compression techniques on the expert's internal parameter matrices to reduce the data movement load, combined with low-cost sparse prediction, achieving perceptible inference acceleration in wall-clock time on resource-constrained devices. Empirically, FloE achieves a 9.3x compression of parameters per expert in Mixtral-8x7B; enables deployment on a GPU with only 11GB VRAM, reducing the memory footprint by up to 8.5x; and delivers a 48.7x inference speedup compared to DeepSpeed-MII on a single GeForce RTX 3090 - all with only a 4.4$\%$ - 7.6$\%$ average performance degradation.

Related papers

• FlashDMoE: Fast Distributed MoE in a Single Kernel [2.246222223318928]
  FlashDMoE is a fully GPU-resident MoE operator that fuses expert computation and inter-GPU communication into a emphsingle persistent GPU kernel.<n>We show that FlashDMoE achieves up to textbf9$times$ higher GPU utilization, textbf6$times$ lower latency, textbf5.7$times$ higher throughput, and textbf4$times$ better overlap efficiency compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-06-05T06:29:14Z)
• 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float [71.43026659686679]
  Large Language Models (LLMs) have grown rapidly in size, creating challenges for efficient deployment on resource-constrained hardware.<n>We introduce Dynamic-Length Float (DFloat11), a compression framework that reduces LLM size by 30% while preserving outputs that are bit-for-bit identical to the original model.
  arXiv  Detail & Related papers  (2025-04-15T22:38:38Z)
• Mixture of Lookup Experts [63.787712153454464]
  Mixture-of-Experts (MoE) activates only a subset of experts during inference.<n>MoLE is a new MoE architecture that is efficient in both communication and VRAM usage.
  arXiv  Detail & Related papers  (2025-03-20T02:31:57Z)
• PIPO: Pipelined Offloading for Efficient Inference on Consumer Devices [13.786008100564185]
  We propose a novel framework, called pipelined offloading (PIPO), for efficient inference on consumer devices.<n>PIPO designs a fine-grained offloading pipeline, complemented with optimized data transfer and computation, to achieve high and efficient scheduling for inference.
  arXiv  Detail & Related papers  (2025-03-15T08:48:38Z)
• eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference [6.642099288463585]
  We propose eMoE, a memory efficient inference system for large language models (LLMs)<n>eMoE reduces memory usage by predicting and loading only the required experts based on recurrent patterns in expert routing.<n>It also enables processing prompts 40x longer, batches 4.5x larger, and achieves 1.5x higher throughput.
  arXiv  Detail & Related papers  (2025-03-10T01:11:52Z)
• HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading [79.38548165722229]
  HEADINFER offloads the KV cache to CPU RAM while avoiding the need to fully store the KV cache for any transformer layer on the GPU.<n>We demonstrate HEADINFER maintains computational efficiency while significantly reducing memory footprint.
  arXiv  Detail & Related papers  (2025-02-18T06:26:05Z)
• 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)
• HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference [54.40808356999408]
  We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference. Our key insight is that dynamically replacing less critical cache-miss experts with low precision versions can substantially reduce expert-loading latency. HOBBIT achieves up to a 9.93x speedup in decoding compared to state-of-the-art MoE offloading systems.
  arXiv  Detail & Related papers  (2024-11-03T04:25:46Z)
• MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models [58.3342517278868]
  This paper describes the design of Mixed-precision AutoRegressive LINear kernels. It shows that batchsizes up to 16-32 can be supported with close to maximum ($4times$) quantization speedup. MarLIN accomplishes this via a combination of techniques, such as asynchronous memory access, complex task scheduling and pipelining.
  arXiv  Detail & Related papers  (2024-08-21T16:10:41Z)
• MEFT: Memory-Efficient Fine-Tuning through Sparse Adapter [40.616849959987555]
  We introduce a novel mechanism that fine-tunes Large Language Models (LLMs) with adapters of larger size yet memory-efficient. This is achieved by leveraging the inherent activation sparsity in the Feed-Forward Networks (FFNs) of LLMs. We employ a Mixture of Experts (MoE)-like architecture to mitigate unnecessary CPU computations and reduce the communication volume between the GPU and CPU.
  arXiv  Detail & Related papers  (2024-06-07T14:49:22Z)
• MoNDE: Mixture of Near-Data Experts for Large-Scale Sparse Models [15.346491299728463]
  MoNDE reduces the volume of MoE parameter movement by transferring only the $textithot$ experts to the GPU. MoNDE enables far more communication-efficient MoE inference, thereby resulting in substantial speedups.
  arXiv  Detail & Related papers  (2024-05-29T07:23:29Z)

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.