mlsanityData to 7 Oct 2026

TurboAngle: Near-Lossless KV Cache Compression via Uniform Angle Quantization

arXiv 2603.27467 ↗First posted 29 Mar 2026cs.LG cs.AIcited by 2

On the map: Efficient LLM inference and serving → KV cache quantization

Abstract (arXiv)

We compress KV cache entries by quantizing angles in the Fast Walsh-Hadamard domain, where a random diagonal rotation makes consecutive element pairs approximately uniformly distributed on the unit circle. We extend this angular quantizer with per-layer early-boost, which independently configures K and V codebook sizes at each layer, allocating higher precision to a model-specific subset of critical layers. Across seven models (1B to 7B parameters), per-layer early-boost achieves lossless compression on four models and near-lossless quality on six of seven, at 3.28 to 3.67 angle bits per element. Asymmetric norm quantization (8-bit for keys, 4-bit log-space for values) yields 6.56 total bits per element on Mistral-7B with perplexity degradation of +0.0014 and no calibration data. A layer-group sensitivity analysis reveals model-specific bottleneck patterns, including K-dominated versus V-dominated layers and negative-transfer layers where increased precision degrades quality.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in KV cache quantization, one of 12 directions in Efficient LLM inference and serving. Builds on 13 of its 16 references that are in the map. First posted on arXiv 29 Mar 2026.

Builds on

13 of 16 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025PolarQuant: Quantizing KV Caches with Polar Transformation4 Feb
  2. 2024QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead5 Jun
  3. 2024KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization7 May
  4. 2024KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache5 Feb
  5. 2024KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization31 Jan

Other references · 8

  1. 2016Pointer Sentinel Mixture Modelscited by 2,992
  2. 2024TinyLlama: An Open-Source Small Language Modelcited by 604
  3. 2024OLMo: Accelerating the Science of Language Modelscited by 599
  4. 2023Textbooks Are All You Need II: phi-1.5 technical reportcited by 559
  5. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 484
  6. 2025SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Modelcited by 307
  7. 2025TurboQuant: Online Vector Quantization with Near-optimal Distortion Ratecited by 116
  8. 2024Stable LM 2 1.6B Technical Reportcited by 86

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inferencecited by 3
  2. 2026A Simple Plug-in for Improving Eviction-Based KV Cache Compressioncited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2026Sequential KV Cache Compression via Probabilistic Language Tries: Beyond the Per-Vector Shannon Limit
  2. 2026OCTOPUS: Optimized KV Cache for Transformers via Octahedral Parametrization Under optimal Squared error quantization
  3. 2026KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation
  4. 2024AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations
  5. 2026SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving
  6. 2026OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond
  7. 2026RoPE-Aware Bit Allocation for KV-Cache Quantization
  8. 2026D-Quant: Driftable Entropy Coding for KV Cache Quantization