mlsanityData to 14 Oct 2026

Revisiting RaBitQ and TurboQuant: A Symmetric Comparison of Methods, Theory, and Experiments

arXiv 2604.19528 ↗First posted 21 Apr 2026cs.LG cs.AI cs.DBcited by 3

Not on the map. Why?

Abstract (arXiv)

This technical note revisits the relationship between RaBitQ and TurboQuant under a unified comparison framework. We compare the two methods in terms of methodology, theoretical guarantees, and empirical performance, using a reproducible, transparent, and symmetric setup. Our results show that, despite the claimed advantage of TurboQuant, TurboQuant performs worse than RaBitQ in most tested settings of inner-product estimation, nearest-neighbor search and KV cache quantization. We further find that several reported runtime and recall results in the TurboQuant paper could not be reproduced from the released implementation under the stated configuration. Overall, this note clarifies the shared structure and genuine differences between the two lines of work, while documenting reproducibility issues in the experimental results reported by the TurboQuant paper.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 11 of its 20 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

11 of 20 references.

References · 11

  1. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  2. 2025TurboQuant: Online Vector Quantization with Near-optimal Distortion Ratecited by 125
  3. 2015Practical and Optimal LSH for Angular Distancecited by 106
  4. 2021EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learningcited by 55
  5. 2021DRIVE: One-bit Distributed Mean Estimationcited by 52
  6. 2024QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overheadcited by 52
  7. 2024RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Searchcited by 48
  8. 2024Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Searchcited by 21
  9. 2017Accelerated Nearest Neighbor Search with Quick ADCcited by 9
  10. 2026GPU-Native Approximate Nearest Neighbor Search with IVF-RaBitQ: Fast Index Build and Searchcited by 4
  11. 2026Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selectioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compressioncited by 2
  2. 2026Block-Sphere Vector Quantizationcited by 0
  3. 2026Fast-TurboQuant: A Multiplier-Free Online Vector Quantization Approachcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Statistical Inference and Quality Measures of KV Cache Quantisations Inspired by TurboQuant
  2. 2026A Note on TurboQuant and the Earlier DRIVE/EDEN Line of Work
  3. 2025LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation
  4. 2025RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm
  5. 2026HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models
  6. 2025XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization
  7. 2024KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
  8. 2026HBQ: Hierarchical Scaling Block Quantization with Hardware-Efficiency-Aware Design for Accurate LLM Inference