# SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding

arXiv: https://arxiv.org/abs/2608.07915 · HTML: https://mlsanity.com/paper/2608.07915/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 8 Aug 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)
- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 26 of 26)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [The case for 4-bit precision: k-bit Inference Scaling Laws](https://mlsanity.com/paper/2212.09720/) (2022)
- [SVD-LLM: Truncation-aware Singular Value Decomposition for Large Language Model Compression](https://mlsanity.com/paper/2403.07378/) (2024)
- [TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate](https://mlsanity.com/paper/2504.19874/) (2025)
- [Eigen Attention: Attention in Low-Rank Space for KV Cache Compression](https://mlsanity.com/paper/2408.05646/) (2024)
- [LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy](https://mlsanity.com/paper/2410.03111/) (2024)
- [RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations](https://mlsanity.com/paper/2501.16383/) (2025)
- [PolarQuant: Quantizing KV Caches with Polar Transformation](https://mlsanity.com/paper/2502.02617/) (2025)
- [Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs](https://mlsanity.com/paper/2502.14837/) (2025)
- [TransMLA: Multi-Head Latent Attention Is All You Need](https://mlsanity.com/paper/2502.07864/) (2025)
- [Accurate KV Cache Quantization with Outlier Tokens Tracing](https://mlsanity.com/paper/2505.10938/) (2025)
- [EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation](https://mlsanity.com/paper/2410.21271/) (2024)
- [From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization](https://mlsanity.com/paper/2604.19884/) (2026)

## Built on by (most cited first, 1 of 1)

- [AnyJev Technical Report](https://mlsanity.com/paper/2610.00831/) (2026)

## Abstract (arXiv)

Large language models (LLMs) increasingly read long inputs in the agentic era, from whole documents and codebases to conversations across many turns. Their inference memory is then dominated by the key-value (KV) cache, the stored attention keys and values of every token the model has read and generated. Because the cache grows with context length and is re-read in full at every generated token, a longer context means more GPU memory. To reduce this cost, most existing methods compress the KV cache by lowering every stored value to the same low precision, a technique known as quantization. They can push this to nearly two bits per value, but rarely further, because quality drops sharply at this 2-bit cliff: four levels are too few for the cache's outlier-heavy values, where a few large entries consume the levels and collapse the rest into noise. A natural remedy is to spend more bits on the channels (feature dimensions) that matter and fewer on the rest, but the raw cache offers no handle: its channels are strongly correlated, so none stands out as more important. Our analysis shows that this handle appears once the cache is rotated into a coordinate system computed from its own statistics, removing these correlations. There, a small fraction of channels carries almost all the information, and spending the budget on those few is far more accurate than spreading it evenly. Guided by this analysis, we develop SPECTRA, a training-free, drop-in codec that re-encodes the cache into this coordinate system and concentrates the bit budget on the channels that carry the signal. On Llama-3.1-8B and Qwen2.5-7B over long-context benchmarks, SPECTRA is near-lossless at 4x compression, competitive at 8x where uniform quantization has collapsed, and reaches up to 12x, pushing usable compression past the 2-bit cliff so the same GPU holds longer contexts and larger batches.