mlsanityData to 14 Oct 2026

TensorDex: A Compact, Tensor-Centric Storage System for Modern AI Models

arXiv 2604.17104 ↗First posted 18 Apr 2026cs.DC cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Modern model hubs store hundreds of petabytes of large language models (LLMs), with fine-tuned variants dominating the storage footprint. These variants contain substantial cross-model redundancy that delta compression can exploit by storing only the difference between a target and a reference model. However, compression effectiveness depends critically on choosing a similar reference. At model-hub scale, this is challenging because model lineage metadata is often missing or unreliable, and different tensors within the same model may be most similar to tensors from different models. Consequently, model-level pairing leaves substantial redundancy unexploited. We present TensorDex, a lossless, tensor-centric storage system that performs delta compression at tensor granularity. TensorDex decomposes models into tensors, uses compact bit-level fingerprints to predict tensor-pair compressibility, and incrementally organizes tensors into multi-center clusters to select effective bases as new models arrive. Evaluated on 2,890 randomly sampled Hugging Face models, TensorDex reduces storage footprint by 70.5%, 37% lower than the state-of-the-art design. It achieves 22.9 GB/s compression and 28.4 GB/s decompression throughput, 3.86x and 1.49x faster than the next-best system, respectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 89 references that are in the map. First posted on arXiv 18 Apr 2026.

Builds on

25 of 89 references.

References · 25

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2024Qwen2.5 Technical Reportcited by 4,942
  3. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  4. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  5. 2025Gemma 3 Technical Reportcited by 1,824
  6. 2022SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Modelscited by 1,386
  7. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,298
  8. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  9. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 526
  10. 2023SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compressioncited by 367
  11. 2019Q8BERT: Quantized 8Bit BERTcited by 300
  12. 2017Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graphcited by 104
13 more
  1. 2024Model Stock: All we need is just a few fine-tuned modelscited by 92
  2. 2023Knowledge is a Region in Weight Space for Fine-tuned Language Modelscited by 58
  3. 2015Optimal Data-Dependent Hashing for Approximate Near Neighborscited by 44
  4. 2024ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Developmentcited by 24
  5. 2023DeltaZip: Efficient Serving of Multiple Full-Model-Tuned LLMscited by 18
  6. 2024ZipNN: Lossless Compression for AI Modelscited by 14
  7. 2025Anatomy of a Machine Learning Ecosystem: 2 Million Models on Hugging Facecited by 12
  8. 2025An Empirical Analysis of Machine Learning Model and Dataset Documentation, Supply Chain, and Licensing Challenges on Hugging Facecited by 6
  9. 2014Dynamic Facility Location via Exponential Clockscited by 5
  10. 2025QStore: Quantization-Aware Compressed Model Storagecited by 5
  11. 2025ZipLLM: Efficient LLM Storage via Model-Aware Synergistic Data Deduplication and Compressioncited by 5
  12. 2025Forecasting Open-Weight AI Model Growth on HuggingFacecited by 3
  13. 2025NeurStore: Efficient In-database Deep Learning Model Management Systemcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework
  2. 2026Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression
  3. 2025Shifting AI Efficiency From Model-Centric to Data-Centric Compression
  4. 2026TensorCast: The Missing Tensor Management Layer in Large Language Model Infrastructure
  5. 2026A Practical Tensor-Network Compression Pipeline for Production-Scale Large Language Models
  6. 2025On Accelerating Edge AI: Optimizing Resource-Constrained Environments
  7. 2024Communication Compression for Tensor Parallel LLM Inference
  8. 2026Large Models for Small Devices: Recent Advances and Empirical Analysis of Edge AI Deployment