Pith. sign in

REVIEW 13 cited by

PolarQuant: Quantizing KV Caches with Polar Transformation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.02617 v1 pith:72FVA3SV submitted 2025-02-04 cs.LG cs.AI

PolarQuant: Quantizing KV Caches with Polar Transformation

classification cs.LG cs.AI
keywords memorypolarpolarquantquantizationembeddingsanglescachedistribution
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large language models (LLMs) require significant memory to store Key-Value (KV) embeddings in their KV cache, especially when handling long-range contexts. Quantization of these KV embeddings is a common technique to reduce memory consumption. This work introduces PolarQuant, a novel quantization method employing random preconditioning and polar transformation. Our method transforms the KV embeddings into polar coordinates using an efficient recursive algorithm and then quantizes resulting angles. Our key insight is that, after random preconditioning, the angles in the polar representation exhibit a tightly bounded and highly concentrated distribution with an analytically computable form. This nice distribution eliminates the need for explicit normalization, a step required by traditional quantization methods which introduces significant memory overhead because quantization parameters (e.g., zero point and scale) must be stored in full precision per each data block. PolarQuant bypasses this normalization step, enabling substantial memory savings. The long-context evaluation demonstrates that PolarQuant compresses the KV cache by over x4.2 while achieving the best quality scores compared to the state-of-the-art methods.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer

    cs.LG 2026-05 unverdicted novelty 7.0

    IVF-TQ replaces learned codebooks with a fixed random rotation and precomputed scalar quantizer in the residual layer of an IVF index, delivering streaming recall stability at fixed bit budgets via a uniform-over-sphe...

  2. Direction-Preserving Number Representations

    cs.LG 2026-05 accept novelty 7.0 partial

    Standard low-precision formats are suboptimal for vector direction preservation compared to optimized scalar alphabets and spherical codes, with gaps quantified analytically and proven in Lean, and NVIDIA's E2M1 nearl...

  3. 3DTurboQuant: Training-Free Near-Optimal Quantization for 3D Reconstruction Models

    cs.CV 2026-04 conditional novelty 7.0

    3DTurboQuant achieves training-free near-optimal quantization for 3DGS and DUSt3R models via random rotations inducing Beta distributions, enabling precomputed Lloyd-Max quantizers that deliver 3.5x and 7.9x compressi...

  4. SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

    cs.AI 2026-04 unverdicted novelty 7.0

    SuperLocalMemory V3.3 implements a cognitive memory taxonomy with mathematical forgetting and multi-channel retrieval, reaching 70.4% on LoCoMo in zero-LLM mode.

  5. OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond

    cs.LG 2026-05 unverdicted novelty 6.0

    OScaR mitigates token norm imbalance via canalized rotation and omni-token scaling to enable near-lossless INT2 KV cache quantization with up to 3x decoding speedup and 5.3x memory reduction.

  6. SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference

    cs.LG 2026-05 unverdicted novelty 6.0

    Spherical KV combines angle-domain attention using spherical key codes with rate-distortion retention to cut KV cache residency and HBM traffic while keeping a paged, fusion-friendly decode path.

  7. SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference

    cs.LG 2026-05 unverdicted novelty 6.0

    Spherical KV introduces angle-domain attention with spherical key parameterization and rate-distortion retention to cut KV cache residency while preserving efficient paged decoding.

  8. Open-TQ-Metal: Fused Compressed-Domain Attention for Long-Context LLM Inference on Apple Silicon

    cs.LG 2026-04 unverdicted novelty 6.0

    Fused compressed-domain int4 attention on Apple Silicon delivers 48x speedup and 3.2x KV cache compression for 128K-context 70B models while matching FP16 token predictions.

  9. eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization

    cs.LG 2026-04 unverdicted novelty 6.0

    eOptShrinkQ compresses KV caches to ~2.2 bits per entry via optimal spectral shrinkage and quantization, outperforming prior methods on LongBench while matching FP16 on multi-needle retrieval.

  10. AXELRAM: Quantize Once, Never Dequantize

    cs.LG 2026-04 conditional novelty 6.0

    AXELRAM performs attention on quantized KV cache using a fixed orthogonal-transform codebook, reducing multiplications by 102.4x and fixing sign-sensitivity spikes via gradient-free calibration.

  11. TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

    cs.LG 2025-04 unverdicted novelty 6.0

    TurboQuant achieves near-optimal vector quantization distortion for both MSE and inner products via random rotation and per-coordinate scalar quantization, with a formal proof that it matches lower bounds within a fac...

  12. IVF-TQ: Calibration-Free Streaming Vector Search via a Codebook-Free Residual Layer

    cs.LG 2026-05 conditional novelty 5.0

    IVF-TQ pairs IVF coarse clustering with a codebook-free TurboQuant-style residual layer to deliver streaming-robust ANN search, supported by multi-seed experiments and an IP-error bound.

  13. Hierarchical vs. Flat Iteration in Shared-Weight Transformers

    cs.CL 2026-04 unverdicted novelty 4.0

    Hierarchical two-speed shared-weight recurrence in Transformers shows a sharp performance gap compared to independent layer stacking in empirical language modeling tests.