Cover Image

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Tianyi, Hariri, Mohsen, Zhong, Shaochen, Chaudhary, Vipin, Sui, Yang, Hu, Xia, Shrivastava, Anshumali
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Floating-Point Data Transformation for Lossless Compression
by: Jamalidinan, Samirasadat, et al.
Published: (2025)

UCCL-Zip: Lossless Compression Supercharged GPU Communication
by: Ma, Shuang, et al.
Published: (2026)

$K^4$: Online Log Anomaly Detection Via Unsupervised Typicality Learning
by: Chen, Weicong, et al.
Published: (2025)

The 1/W Law: An Analytical Study of Context-Length Routing Topology and GPU Generation Gains for LLM Inference Energy Efficiency
by: Chen, Huamin, et al.
Published: (2026)

Empowering Distributed Training with Sparsity-driven Data Synchronization
by: Wang, Zhuang, et al.
Published: (2023)

LIME:Accelerating Collaborative Lossless LLM Inference on Memory-Constrained Edge Devices
by: Sun, Mingyu, et al.
Published: (2025)

Boosting Scientific Error-Bounded Lossy Compression through Optimized Synergistic Lossy-Lossless Orchestration
by: Wu, Shixun, et al.
Published: (2025)

EXaCTz: Guaranteed Extremum Graph and Contour Tree Preservation for Distributed- and GPU-Parallel Lossy Compression
by: Li, Yuxiao, et al.
Published: (2026)

Hypergraph Partitioning on GPU with Distinct Incident Hyperedges and Size Constraints
by: Ronzani, Marco, et al.
Published: (2026)

ParvaGPU: Efficient Spatial GPU Sharing for Large-Scale DNN Inference in Cloud Environments
by: Lee, Munkyu, et al.
Published: (2024)

NCCLZ: Compression-Enabled GPU Collectives with Decoupled Quantization and Entropy Coding
by: Wang, Jiamin, et al.
Published: (2026)

gZCCL: Compression-Accelerated Collective Communication Framework for GPU Clusters
by: Huang, Jiajun, et al.
Published: (2023)

HAS-GPU: Efficient Hybrid Auto-scaling with Fine-grained GPU Allocation for SLO-aware Serverless Inferences
by: Gu, Jianfeng, et al.
Published: (2025)

PVU: Design and Implementation of a Posit Vector Arithmetic Unit (PVU) for Enhanced Floating-Point Computing in Edge and AI Applications
by: Wu, Xinyu, et al.
Published: (2025)

PipeMax: Enhancing Offline LLM Inference on Commodity GPU Servers
by: Zhang, Hongbin, et al.
Published: (2026)

FloatSOM: GPU-Accelerated, Distributed, Topology-Flexible Self-Organizing Maps
by: Xu, Tony, et al.
Published: (2026)

MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model?
by: Ma, Songkai, et al.
Published: (2025)

HarMoEny: Efficient Multi-GPU Inference of MoE Models
by: Doucet, Zachary, et al.
Published: (2025)

Torpor: GPU-Enabled Serverless Computing for Low-Latency, Resource-Efficient Inference
by: Yu, Minchen, et al.
Published: (2023)

ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs
by: Yang, Jinwu, et al.
Published: (2026)

GPU Volume Rendering with Hierarchical Compression Using VDB
by: Zellmann, Stefan, et al.
Published: (2025)

Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLM
by: Zhang, Biyao, et al.
Published: (2025)

KIS-S: A GPU-Aware Kubernetes Inference Simulator with RL-Based Auto-Scaling
by: Zhang, Guilin, et al.
Published: (2025)

APEX: Asynchronous Parallel CPU-GPU Execution for Online LLM Inference on Constrained GPUs
by: Fan, Jiakun, et al.
Published: (2025)

DAK: Direct-Access-Enabled GPU Memory Offloading with Optimal Efficiency for LLM Inference
by: Lin, Shouxu, et al.
Published: (2026)

FourierCompress: Layer-Aware Spectral Activation Compression for Efficient and Accurate Collaborative LLM Inference
by: Ma, Jian, et al.
Published: (2025)

Loki: A System for Serving ML Inference Pipelines with Hardware and Accuracy Scaling
by: Ahmad, Sohaib, et al.
Published: (2024)

Efficient CPU-GPU Collaborative Inference for MoE-based LLMs on Memory-Limited Systems
by: Huang, En-Ming, et al.
Published: (2025)

SiPipe: Bridging the CPU-GPU Utilization Gap for Efficient Pipeline-Parallel LLM Inference
by: He, Yongchao, et al.
Published: (2025)

KV Cache Compression for Inference Efficiency in LLMs: A Review
by: Liu, Yanyu, et al.
Published: (2025)

LoHan: Low-Cost High-Performance Framework to Fine-Tune 100B Model on a Consumer GPU
by: Liao, Changyue, et al.
Published: (2024)

ZipCCL: Efficient Lossless Data Compression of Communication Collectives for Accelerating LLM Training
by: Lin, Wenxiang, et al.
Published: (2026)

SIMPLE: Disaggregating Sampling from GPU Inference into a Decision Plane for Faster Distributed LLM Serving
by: Zhao, Bohan, et al.
Published: (2025)

SpecInF: Exploiting Idle GPU Resources in Distributed DL Training via Speculative Inference Filling
by: Lv, Cunchi, et al.
Published: (2025)

RL over Commodity Networks: Overcoming the Bandwidth Barrier with Lossless Sparse Deltas
by: Ruan, Chaoyi, et al.
Published: (2026)

Scaling Up Throughput-oriented LLM Inference Applications on Heterogeneous Opportunistic GPU Clusters with Pervasive Context Management
by: Phung, Thanh Son, et al.
Published: (2025)

Heimdall++: Optimizing GPU Utilization and Pipeline Parallelism for Efficient Single-Pulse Detection
by: Xia, Bingzheng, et al.
Published: (2025)

FedOptimus: Optimizing Vertical Federated Learning for Scalability and Efficiency
by: Shrivastava, Nikita, et al.
Published: (2025)

Parallel Collaborative ADMM Privacy Computing and Adaptive GPU Acceleration for Distributed Edge Networks
by: Xia, Mengchun, et al.
Published: (2026)

Efficiently Executing High-throughput Lightweight LLM Inference Applications on Heterogeneous Opportunistic GPU Clusters with Pervasive Context Management
by: Phung, Thanh Son, et al.
Published: (2025)